Minara Crypto Trading and Wallet
Minara-AI/minara-skills
Drives the Minara CLI for crypto swaps, perps, limit orders, wallet transfers, deposits and withdrawals, plus AI market analysis.
Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents
MITAuto-check passed
Install Account Validation
$ npx skills add PlamenTSV/plamen --skill account-validation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PlamenTSV/plamen account-validation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/PlamenTSV/plamen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/solana/account-validation .claude/skills/account-validation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "account-validation" agent skill from https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validation into .claude/skills/account-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-validation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add PlamenTSV/plamen --skill account-validation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PlamenTSV/plamen account-validation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PlamenTSV/plamen.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agents/skills/solana/account-validation .agents/skills/account-validation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "account-validation" agent skill from https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validation into .agents/skills/account-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-validation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PlamenTSV/plamen --skill account-validation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PlamenTSV/plamen account-validation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PlamenTSV/plamen.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agents/skills/solana/account-validation .cursor/skills/account-validation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "account-validation" agent skill from https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validation into .cursor/skills/account-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-validation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/PlamenTSV/plamen.git --path agents/skills/solana/account-validation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add PlamenTSV/plamen --skill account-validation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PlamenTSV/plamen account-validation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PlamenTSV/plamen.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agents/skills/solana/account-validation .gemini/skills/account-validation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "account-validation" agent skill from https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validation into .gemini/skills/account-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-validation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install PlamenTSV/plamen account-validationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add PlamenTSV/plamen --skill account-validation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PlamenTSV/plamen.git skills-src && mkdir -p .github/skills && cp -r skills-src/agents/skills/solana/account-validation .github/skills/account-validation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "account-validation" agent skill from https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validation into .github/skills/account-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-validation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PlamenTSV/plamen --skill account-validation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PlamenTSV/plamen account-validation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PlamenTSV/plamen.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agents/skills/solana/account-validation .opencode/skills/account-validation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "account-validation" agent skill from https://github.com/PlamenTSV/plamen/tree/main/agents/skills/solana/account-validation into .opencode/skills/account-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "account-validation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
account-validation- GitHub stars
- 303
- Token cost
- ~1.7k tokens
- SKILL.md length
- 663 words
- Files
- 1
- Skills in repo
- 87
- Repo updated
- First seen
- Licence
- MIT
At a glance
Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents
- Works in 8 steps: Account Type Inventory → Owner Check Audit → Discriminator Check → …
- Pattern Always required for Solana audits - Inject Into Breadth agents
- SKILL.md covers 1. Account Type Inventory, 2. Owner Check Audit, 3. Discriminator Check and 4. Data Matching…, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Account Validation is an agent skill from PlamenTSV/plamen. Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Solana. The repository describes itself as: Autonomous Web3 security audit agent for Claude Code. The licence is MIT.
When your agent uses it
- Pattern Always required for Solana audits - Inject Into Breadth agents
Example prompts
- “/account-validation”
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 795962b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Account Validation loads about 1.7k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 663 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from PlamenTSV/plamen at commit 795962b, republished under its MIT licence (© PlamenTSV). 663 words, ~1,727 tokens.
Download SKILL.mdSave it as
.claude/skills/account-validation/SKILL.md (or your agent's skills folder).- name
- account-validation
- description
- Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents
ACCOUNT_VALIDATION Skill
Trigger Pattern: Always required for Solana audits Inject Into: Breadth agents, depth agents Finding prefix:
[AV-N]Rules referenced: S1, S6, S7, S8, R4
For every instruction handler in the Solana program:
1. Account Type Inventory
For EACH instruction, list every account with expected constraints:
| # | Account Name | Expected Owner | Expected Type (Discriminator) | Mutable? | Signer? | Constraints (has_one, seeds, etc.) |
|---|---|---|---|---|---|---|
| 1 | {name} | {program_id / system / token} | {Account<T> / UncheckedAccount / etc.} | YES/NO | YES/NO | {list all} |
Anchor auto-checks: Anchor's Account<T> validates owner + discriminator automatically. UncheckedAccount / AccountInfo do NOT - manual validation required.
2. Owner Check Audit
For each AccountInfo or UncheckedAccount usage:
| Account | Owner Validated? | Validation Location | Correct Owner? | Missing? |
|---|---|---|---|---|
| {name} | YES/NO | {line} | {expected vs actual} | FLAG if NO |
Critical pattern: Any AccountInfo deserialized without prior owner check → arbitrary data injection.
Anchor pattern: #[account(owner = expected_program)] or manual require!(account.owner == &expected_id).
3. Discriminator Check
For all accounts deserialized from raw data:
| Account | Uses Account<T>? | Discriminator Checked? | Can Substitute Different Account Type? |
|---|---|---|---|
| {name} | YES/NO | YES/NO (Anchor auto) | {if NO: what types could be substituted} |
Attack: Pass an account of Type B where Type A is expected - different data layout, fields interpreted incorrectly.
Safe: Anchor's Account<T> checks the 8-byte discriminator. Manual programs must check explicitly.
Anchor IDL buffer amplification: If the program uses Anchor with the default IDL feature enabled (check Cargo.toml for idl-build feature or absence of no-idl — enabled by default), IdlCreateBuffer is a permissionless instruction that lets ANYONE create program-owned accounts with nearly arbitrary data at arbitrary lengths. This means a missing discriminator check is exploitable even when no other account type in the program has a suitable layout for cosplay — the attacker crafts one via IdlCreateBuffer. When flagging a discriminator bypass: if IDL feature is enabled, severity is NOT mitigated by "no suitable account type exists for substitution."
4. Data Matching (Cross-Account References)
For each cross-account reference (has_one, constraint, seeds):
| Instruction | Account A | Account B | Relationship | Validated? | Bypass? |
|---|---|---|---|---|---|
| {ix} | {a} | {b} | {a.field == b.key()} | YES/NO | {if NO: how to exploit} |
Pattern: Ensure that when Account A references Account B (e.g., vault.mint == mint.key()), the relationship is enforced on-chain.
Attack: Substitute a different mint account that the vault doesn't actually belong to.
5. Remaining Accounts Audit
For each use of ctx.remaining_accounts:
| Instruction | Remaining Account Usage | Owner Validated? | Type Validated? | Signer Checked? | Data Validated? |
|---|---|---|---|---|---|
| {ix} | {purpose} | YES/NO | YES/NO | YES/NO | YES/NO |
Critical: remaining_accounts bypass Anchor's automatic validation. Every field must be checked manually.
Attack: Inject attacker-controlled accounts via remaining_accounts to redirect funds or corrupt state.
Show full SKILL.md (260 more words)Show less
6. Duplicate Account Detection
For each instruction with 2+ mutable accounts:
| Instruction | Mutable Account A | Mutable Account B | Key Uniqueness Enforced? | Self-Transfer Risk? |
|---|---|---|---|---|
| {ix} | {a} | {b} | YES/NO | {if NO: impact of a==b} |
Attack (S7): Pass the same account as both from and to in a transfer → potential balance inflation.
Defense: require!(account_a.key() != account_b.key()) or Anchor constraint.
7. Sysvar Validation
For each sysvar account passed as input:
| Sysvar | Passed As | Address Validated? | Could Be Spoofed? |
|---|---|---|---|
| Clock | AccountInfo | YES/NO | {if NO: attacker controls time} |
| Rent | AccountInfo | YES/NO | {if NO: attacker controls rent} |
| Instructions | AccountInfo | YES/NO | {if NO: Wormhole-style attack} |
Safe pattern: Use Sysvar::from_account_info() or _checked variants.
Unsafe pattern: Raw deserialization of sysvar data from unchecked AccountInfo.
8. Trust Chain Analysis
For each account validation chain, trace to its root:
| Account | Validated Against | Root Trust Anchor | Chain Complete? |
|---|---|---|---|
| {account} | {what validates it} | PDA / Program ID / Hardcoded pubkey / NONE | YES/NO |
Pattern: Validation chain must root in a known-good value. If chain roots in user input → FINDING.
Example: authority validated against vault.authority, vault validated against PDA seeds → chain roots in PDA (good).
Finding Template
**ID**: [AV-N]
**Severity**: [based on what attacker can do with invalid account]
**Step Execution**: ✓1,2,3,4,5,6,7,8 | ✗(reasons) | ?(uncertain)
**Rules Applied**: [S1:✓, S6:✓/✗, S7:✓/✗, S8:✓/✗, R4:✓/✗]
**Location**: program/src/instructions/{file}.rs:LineN
**Title**: Missing [validation type] for [account] in [instruction] enables [attack]
**Description**: [Specific missing validation with code reference]
**Impact**: [What attacker can achieve: fund theft, state corruption, DoS]Step Execution Checklist (MANDATORY)
| Section | Required | Completed? | Notes |
|---|---|---|---|
| 1. Account Type Inventory | YES | ✓/✗/? | For every instruction |
| 2. Owner Check Audit | YES | ✓/✗/? | For every AccountInfo/UncheckedAccount |
| 3. Discriminator Check | YES | ✓/✗/? | For all deserialized accounts |
| 4. Data Matching | YES | ✓/✗/? | For all cross-account references |
| 5. Remaining Accounts Audit | IF remaining_accounts used | ✓/✗(N/A)/? | Manual validation check |
| 6. Duplicate Account Detection | YES | ✓/✗/? | For all mutable account pairs |
| 7. Sysvar Validation | IF sysvars passed as AccountInfo | ✓/✗(N/A)/? | Address validation |
| 8. Trust Chain Analysis | YES | ✓/✗/? | Chain to root trust anchor |
© PlamenTSV, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in agents/skills/solana/account-validation of PlamenTSV/plamen.
Open the folder on GitHubat commit 795962b
Compare with similar skills
Account Validation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Account Validation this skillPlamenTSV/plamen | 303 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Minara Crypto Trading and WalletMinara-AI/minara-skills | 358 | 1 repos | ~5.7k | Automated safety check: Pass | None | |
| NEAR Intents Swap Integrationinternet-court/internet-court-skill | 6.4k | 2 repos | ~939 | Automated safety check: Pass | Custom licence | |
| Solana Devsolana-foundation/solana-dev-skill | 574 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Meme Coin Security Auditawarexone/Agentic-Bug-Hunter | 5.3k | 1 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Swapper Depositswapperfinance/swapper-toolkit | 852 | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
NEAR Intents Swap Integration
internet-court/internet-court-skill
Builds cross-chain token swaps and bridge flows with the NEAR Intents 1Click API: quotes, deposit addresses, per-chain deposits and status polling.
Solana Dev
solana-foundation/solana-dev-skill
A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my…
Meme Coin Security Audit
awarexone/Agentic-Bug-Hunter
Screens EVM and Solana meme coins for rug pull signs such as hidden mint, honeypot logic and fee tricks, starting with fast kill signals before any code review.
Swapper Deposit
swapperfinance/swapper-toolkit
Deposit and bridge funds into a wallet or protocol using Swapper Finance.
PNP Prediction Markets on Solana
internet-court/internet-court-skill
Creates, trades and settles permissionless prediction markets on Solana with any SPL token as collateral, including social-media and custom-oracle markets.
More from PlamenTSV/plamen
All 87 skills in this repoAudit Prep
PlamenTSV/plamen
Prepare Solidity projects for a security audit — test coverage, test quality, NatSpec docs, code hygiene, dependency health, best-practice enforcement, deployment readiness, and project…
Verification Protocol
PlamenTSV/plamen
Trigger Pattern Always (used by all verifier agents) - Inject Into security-verifier agents (Phase 5)
Ability Analysis
PlamenTSV/plamen
Trigger Pattern Always (Aptos Move) - foundational security check - Inject Into Breadth agents, depth agents
Ability Analysis
PlamenTSV/plamen
Trigger Pattern Always (Sui Move) -- foundational security check - Inject Into Breadth agents, depth agents
Account Lifecycle
PlamenTSV/plamen
Trigger Pattern ACCOUNTCLOSING flag detected (close/CloseAccount usage) - Inject Into Breadth agents, depth agents
Auth Validation
PlamenTSV/plamen
Trigger Pattern Always required for Soroban audits - Inject Into Breadth agents, depth agents
Related
Works with
Questions about Account Validation
What does Account Validation do?
Trigger Pattern Always required for Solana audits - Inject Into Breadth agents, depth agents. Account Validation is an agent skill from PlamenTSV/plamen.
When should I use Account Validation?
Account Validation fits situations like: pattern Always required for Solana audits - Inject Into Breadth agents.
How do I install Account Validation in Claude Code?
Run `npx skills add PlamenTSV/plamen --skill account-validation -a claude-code`. Or copy the skill folder (agents/skills/solana/account-validation in PlamenTSV/plamen) into .claude/skills/account-validation in your project. Claude Code loads it when a task matches its description.
How do I install Account Validation in Codex?
Run `npx skills add PlamenTSV/plamen --skill account-validation -a codex`. Or copy the skill folder (agents/skills/solana/account-validation in PlamenTSV/plamen) into .agents/skills/account-validation in your project. Codex loads it when a task matches its description.
Can I use Account Validation in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PlamenTSV/plamen --skill account-validation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/account-validation, .gemini/skills/account-validation, .github/skills/account-validation and .opencode/skills/account-validation in your project.
What does Account Validation need to run?
SKILL.md names no scripts, command-line tools or credentials: Account Validation is instructions for the agent only.
Does Account Validation access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Account Validation safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Account Validation use?
Account Validation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Account Validation use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Account Validation?
Skills that share tags, products or a category with Account Validation: Minara Crypto Trading and Wallet (Minara-AI/minara-skills, 358 stars), NEAR Intents Swap Integration (internet-court/internet-court-skill, 6.4k stars), Solana Dev (solana-foundation/solana-dev-skill, 574 stars) and Meme Coin Security Audit (awarexone/Agentic-Bug-Hunter, 5.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Account Validation?
PlamenTSV (a GitHub user) maintains it in PlamenTSV/plamen, which has 303 GitHub stars. The repository holds 87 skills in this directory. The repository was last updated on September 26, 2026.
Source: PlamenTSV/plamen on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.