create-agents-md

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to manage documentation in AGENTS.md and CLAUDE.md. It performs file read/write operations within the project root to synchronize style guide content.- [DATA_EXPOSURE]: The skill scans for common configuration files (e.g., package.json, pyproject.toml, Cargo.toml) to identify the project's programming languages. This metadata is used locally to select appropriate style guides and is not transmitted externally.- [EXTERNAL_DOWNLOADS]: The skill references a GitHub repository (github.com/gemini-cli-extensions/conductor) for attribution in the generated documentation. However, it does not perform any network downloads; the style guide content is sourced from local Markdown files provided within the skill's references/ directory.- [INDIRECT_PROMPT_INJECTION]: The skill modifies AGENTS.md based on existing content. It uses specific HTML comments (<!-- create-agents-md:code-styleguides:start -->) as boundary markers to safely identify and replace its own generated sections. Furthermore, the skill requires explicit user confirmation before applying any changes to the filesystem, providing a manual verification step.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:42 PM