Security Review

What it does

When your agent uses it

• Asked to security review
• Find vulnerabilities
• Check for security issues
• Review code for injection

Example prompts

• “security review”
• “find vulnerabilities”
• “check for security issues”
• “/security-review”

Requirements

• A credential in BETTER_AUTH_SECRET
• A credential in STEAM_API_KEY
• Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash(read-only commands like cargo, git, npm)

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Detect Context and Load References
2. 2Map Data Flow
3. 3Verify Exploitability
4. 4Classify Severity

What it can do on your machine

Read from SKILL.md and the folder at commit e5a8f5e. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • Bash(read-only commands like cargo
  • git
  • npm)

  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 and rust).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • cheatsheetseries.owasp.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • BETTER_AUTH_SECRET
  • STEAM_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Security Review loads about 1.8k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 433 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~92

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~12k

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

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 deadlock-mod-manager/deadlock-mod-manager at commit e5a8f5e, republished under its CC-BY-SA-4.0 licence (© deadlock-mod-manager). 433 words, ~1,811 tokens.

name

security-review

description

Security code review for Tauri/Rust/TypeScript desktop apps and Hono/oRPC APIs. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", or review code for injection, XSS, IPC abuse, path traversal, or authentication issues. Provides confidence-based reporting tuned to the Deadlock Mod Manager stack.

allowed-tools

Read, Glob, Grep, Bash(read-only commands like cargo, git, npm)

<!--
Reference material based on OWASP Cheat Sheet Series (CC BY-SA 4.0)
https://cheatsheetseries.owasp.org/
-->

# Rust — command injection
Command::new(user_input)
Command::new("sh").arg("-c").arg(format!("... {}", user_input))

# Rust — path traversal (no canonicalize + prefix check)
std::fs::read(format!("{}/{}", base, user_filename))

# Rust — unsafe in IPC handlers
unsafe { } // inside #[tauri::command]

# TypeScript — XSS escalation to native
dangerouslySetInnerHTML={{ __html: modDescription }}
eval(serverData)
window.__TAURI__.invoke(userControlledCommand)

# API — SQL injection via string interpolation
sql`SELECT * FROM mods WHERE name = '${userInput}'`

# Secrets hardcoded in source
BETTER_AUTH_SECRET = "..."
STEAM_API_KEY = "..."
DATABASE_URL = "postgres://user:pass@..."

# File ops — safe if path is validated + canonicalized
std::fs::read_to_string(path)
std::fs::write(path, data)

# Process spawn — safe if args are hardcoded/validated
Command::new("steam").arg(game_id)

# Drizzle — safe when using query builder
db.select().from(mods).where(eq(mods.name, input))

# React rendering — safe if data doesn't reach dangerous sink
<div>{modData.description}</div>

## Security Review: [Component/File Name]

### Summary

- **Findings**: X (Y Critical, Z High, ...)
- **Risk Level**: Critical/High/Medium/Low
- **Confidence**: High/Mixed
- **Scope**: [What was reviewed]

### Findings

#### [VULN-001] [Vulnerability Type] (Severity)

- **Location**: `file.rs:123`
- **Confidence**: High/Medium
- **Issue**: [One-line description]
- **Data Flow**: [source] → [transforms] → [sink]
- **Impact**: [What an attacker achieves]
- **Evidence**:
  ```rust
  // vulnerable code
  ```

If no vulnerabilities found: "No high-confidence vulnerabilities identified."

© deadlock-mod-manager, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in .agents/skills/security-review of deadlock-mod-manager/deadlock-mod-manager.

• SKILL.md
• LICENSE
• references/api-security.md
• references/authentication.md
• references/cryptography.md
• references/file-operations.md
• references/rust-backend.md
• references/supply-chain.md
• references/tauri-ipc.md
• references/webview-xss.md

Open the folder on GitHubat commit e5a8f5e