Agent skill

Codeql Audit

by deonmenezes in deonmenezes/mantishack

Build a CodeQL database and run dataflow-backed query-suite analysis via the mantiscodeql MCP server

Apache-2.0Auto-check passedSecurity

Install Codeql Audit

skills CLI
$ npx skills add deonmenezes/mantishack --skill codeql-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install deonmenezes/mantishack codeql-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/deonmenezes/mantishack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/codeql-audit .claude/skills/codeql-audit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
codeql-audit
GitHub stars
505
Token cost
~325 tokens
SKILL.md length
146 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Build a CodeQL database and run dataflow-backed query-suite analysis via the mantiscodeql MCP server

  • Works in 4 steps: codeql_create_database({ source_root,… → codeql_analyze({ database_path,… → Treat every SARIF result as a candidate… → …
  • Tasks that involve Static analysis and SAST
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Codeql Audit is an agent skill from deonmenezes/mantishack. Build a CodeQL database and run dataflow-backed query-suite analysis via the mantiscodeql MCP server

Its SKILL.md is about 330 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Static analysis and SAST. It works with Model Context Protocol. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Static analysis and SAST

Example prompts

  • “/codeql-audit”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. codeql_create_database({ source_root, language, database_path }) once per target/language. This is slow (can take minutes on large repos)…
  2. codeql_analyze({ database_path, query_suite }). Default query_suite is "security-extended"; use "security-and-quality" only if the user…
  3. Treat every SARIF result as a candidate with a dataflow-backed path, which is stronger recall evidence than a plain grep match -- but it…
  4. If codeql reports available: false, fall back to semgrep_scan and program-analysis's source_sink_scan/ast_grep_scan for recall, and tell…

What it can do on your machine

Read from SKILL.md and the folder at commit c3a2e68. 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.

    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

Codeql Audit loads about 325 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 146 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~325

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 deonmenezes/mantishack at commit c3a2e68, republished under its Apache-2.0 licence (© deonmenezes). 146 words, ~325 tokens.

Download SKILL.mdSave it as .claude/skills/codeql-audit/SKILL.md (or your agent's skills folder).
name
codeql-audit
description
Build a CodeQL database and run dataflow-backed query-suite analysis via the mantis_codeql MCP server

Use codeql_create_database then codeql_analyze (mantis_codeql MCP server) when you need dataflow-aware SAST beyond what regex/pattern tools (semgrep, ast-grep) can prove -- CodeQL's query suites trace actual source-to-sink data flow through the codebase.

Workflow:

  1. codeql_create_database({ source_root, language, database_path }) once per target/language. This is slow (can take minutes on large repos); don't repeat it unless the source changed.
  2. codeql_analyze({ database_path, query_suite }). Default query_suite is "security-extended"; use "security-and-quality" only if the user wants broader quality findings too.
  3. Treat every SARIF result as a candidate with a dataflow-backed path, which is stronger recall evidence than a plain grep match -- but it is still not a confirmed finding. CodeQL's own dataflow models can miss framework-specific sanitization; verify the path manually before validating.
  4. If codeql reports available: false, fall back to semgrep_scan and program-analysis's source_sink_scan/ast_grep_scan for recall, and tell the user CodeQL-grade dataflow coverage wasn't available for this run.

© deonmenezes, Apache-2.0. 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 .codex/skills/codeql-audit of deonmenezes/mantishack.

Open the folder on GitHubat commit c3a2e68

Compare with similar skills

Codeql Audit 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.

Codeql Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codeql Audit this skilldeonmenezes/mantishack505—~325Automated safety check: PassApache-2.0
Ida Reversesickn33/agentic-awesome-skills47k1 repos~3.1kAutomated safety check: PassMIT
Cpg Analysisalinaqi/maggy707—~2kAutomated safety check: PassMIT
Agent Bom RegistryLeoYeAI/openclaw-master-skills2.2k—~969Automated safety check: PassApache-2.0
Secknowledge SkillPa55w0rd/secknowledge-skill423—~2.7kAutomated safety check: PassNone
Evm Audit Flowmtarcure/claude-vibe-squad163—~1.5kAutomated safety check: PassMIT

Similar skills

  • Ida Reverse

    sickn33/agentic-awesome-skills

    Reverse engineer binaries with IDA Pro: decompilation, disassembly, data-flow tracking, cross-references, and IDA MCP automation for deep static analysis of PE/ELF/Mach-O targets.

    47k GitHub starsUsed in 1 repo~3.1k tokens
    SecurityAuto-check passed
  • Cpg Analysis

    alinaqi/maggy

    Deep code property graph analysis with Joern CPG (AST+CFG+PDG) and CodeQL for control flow, data flow, taint analysis, and security auditing

    707 GitHub stars~2k tokensUpdated 14 days ago
    SecurityAuto-check passed
  • Agent Bom Registry

    LeoYeAI/openclaw-master-skills

    MCP server security registry and trust assessment — look up servers in the 427+ server security metadata registry, run pre-install marketplace checks, batch fleet risk scoring, assess skill file…

    2.2k GitHub stars~969 tokensUpdated 2 mo ago
    SecurityAuto-check passed
  • Secknowledge Skill

    Pa55w0rd/secknowledge-skill

    Web+AI 安全测试知识库。融合 WooYun 88,636 案例 + 先知 L1-L4 方法论 + GAARM 173 风险 + OWASP Top 10 (LLM/ASI/WSTG)。

    423 GitHub stars~2.7k tokensUpdated 3 mo ago
    SecurityAuto-check passed
  • Evm Audit Flow

    mtarcure/claude-vibe-squad

    A skill your agent uses when you have a Foundry or Hardhat repository of Solidity or Vyper contracts and want the end-to-end EVM review workflow on native CLIs — a slither static pass, semgrep taint…

    163 GitHub stars~1.5k tokensUpdated 17 days ago
    SecurityAuto-check passed
  • Architecture

    pikax/verter

    Verter codebase architecture: high-level module map, TypeScript packages, plugin system, CSS analysis, MCP server, static analysis types

    112 GitHub stars~5.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from deonmenezes/mantishack

All 11 skills in this repo
  • Codex Issue Digest

    deonmenezes/mantishack

    Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows.

    505 GitHub stars~2.3k tokensUpdated 5 days ago
    Auto-check passed
  • Codex Bug

    deonmenezes/mantishack

    Diagnose GitHub bug reports in openai/codex. An agent skill from deonmenezes/mantishack.

    505 GitHub stars~643 tokensUpdated 5 days ago
    Auto-check passed
  • Detection Breadth

    deonmenezes/mantishack

    When and how to reach for the companion detectors -- bandit (Python SAST) and trivy (deps + secrets + IaC misconfig) -- alongside the core semgrep/CodeQL/osv/trufflehog toolchain

    505 GitHub stars~510 tokensUpdated 5 days ago
    Auto-check passed
  • HTTP Evidence

    deonmenezes/mantishack

    Turn a captured HTTP request/response into a bounded, redacted evidence pack with a stable request-ref using the mantishttpaudit MCP server, instead of pasting raw traffic into a finding

    505 GitHub stars~455 tokensUpdated 5 days ago
    Auto-check passed
  • Program Analysis

    deonmenezes/mantishack

    Use astgrepscan, sourcesinkscan, and smtcheckreachability (mantisprogramanalysis MCP server) to move a candidate toward a proven-reachable finding

    505 GitHub stars~551 tokensUpdated 5 days ago
    Auto-check passed
  • Canary Tripwire Response

    deonmenezes/mantishack

    What to do if a mantiscanary decoy tool ever shows up as tempting or gets called -- treat it as a security incident, not a normal tool result

    505 GitHub stars~376 tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Codeql Audit

What does Codeql Audit do?

Build a CodeQL database and run dataflow-backed query-suite analysis via the mantiscodeql MCP server. Codeql Audit is an agent skill from deonmenezes/mantishack.

When should I use Codeql Audit?

Codeql Audit fits situations like: tasks that involve Static analysis and SAST.

How do I install Codeql Audit in Claude Code?

Run `npx skills add deonmenezes/mantishack --skill codeql-audit -a claude-code`. Or copy the skill folder (.codex/skills/codeql-audit in deonmenezes/mantishack) into .claude/skills/codeql-audit in your project. Claude Code loads it when a task matches its description.

How do I install Codeql Audit in Codex?

Run `npx skills add deonmenezes/mantishack --skill codeql-audit -a codex`. Or copy the skill folder (.codex/skills/codeql-audit in deonmenezes/mantishack) into .agents/skills/codeql-audit in your project. Codex loads it when a task matches its description.

Can I use Codeql Audit 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 deonmenezes/mantishack --skill codeql-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codeql-audit, .gemini/skills/codeql-audit, .github/skills/codeql-audit and .opencode/skills/codeql-audit in your project.

What does Codeql Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Codeql Audit is instructions for the agent only.

Does Codeql Audit 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 Codeql Audit 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 Codeql Audit use?

Codeql Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codeql Audit use?

About 325 tokens (SKILL.md is roughly 1.3k 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 Codeql Audit?

Skills that share tags, products or a category with Codeql Audit: Ida Reverse (sickn33/agentic-awesome-skills, 47k stars), Cpg Analysis (alinaqi/maggy, 707 stars), Agent Bom Registry (LeoYeAI/openclaw-master-skills, 2.2k stars) and Secknowledge Skill (Pa55w0rd/secknowledge-skill, 423 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codeql Audit?

deonmenezes (a GitHub user) maintains it in deonmenezes/mantishack, which has 505 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 3, 2026.

Source: deonmenezes/mantishack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.