dewey-docs
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the @arach/dewey package from the NPM registry. As 'arach' is the verified author of the skill, this is documented as a vendor-provided resource.
- [COMMAND_EXECUTION]: The skill uses several CLI commands for project initialization and file generation, including 'dewey init', 'dewey generate', and 'dewey create'. It also suggests standard installation commands like 'npm install' and 'pnpm add'.
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8). * Ingestion points: The tool reads source markdown files from the ./docs directory. * Boundary markers: The skill documentation does not mention delimiters or instructions to ignore embedded agent commands in the source markdown. * Capability inventory: The associated CLI tool writes multiple documentation files (AGENTS.md, llms.txt, docs.json) and scaffolds complete static sites. * Sanitization: There is no mention of sanitization or filtering for the source markdown content before it is incorporated into the agent-optimized files.
Audit Metadata