md-docs
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
git ls-files,git rev-parse,cp,mv, andln -sfto discover project files, perform backups, and manage symlinks for documentation context files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project files to generate or update documentation, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads content from existing markdown files (
README.md,CLAUDE.md,AGENTS.md,CONTRIBUTING.md,DOCS.md) and project manifests (package.json,pyproject.toml,composer.json). - Boundary markers: No explicit delimiters or "ignore embedded instructions" warnings are used when interpolating file content into prompts or context files.
- Capability inventory: The skill has capabilities for file reading, file writing, and local command execution via shell tools (git, filesystem utilities).
- Sanitization: While the skill includes instructions to verify factual claims against the codebase, it does not implement explicit sanitization or filtering of the processed text to prevent malicious instructions from being executed by the agent.
Audit Metadata