docs-codebase
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a collection of high-quality documentation templates and technical writing guides. It promotes best practices for secret management by using clear placeholders (e.g.,
YOUR_ACCESS_TOKEN) and recommending the use of environment variable files (.env) instead of hardcoding credentials. - [EXTERNAL_DOWNLOADS]: The skill references and provides configuration for various well-known documentation and linting tools such as MkDocs, Docusaurus, Vale, markdownlint, and cspell. These references are informative and consistent with the skill's intended purpose of improving documentation quality.
- [INDIRECT_PROMPT_INJECTION]: As a tool designed to read and restructure existing repository documentation, the skill possesses an attack surface for indirect prompt injection from potentially malicious content within a codebase.
- Ingestion points: Documentation files throughout the repository (e.g., README.md, files in docs/).
- Boundary markers: The skill emphasizes structural delimiters like headings and canonical paths but does not explicitly provide instructions for isolating or escaping untrusted data during processing.
- Capability inventory: The skill's operations are limited to documentation analysis and writing. It lacks capabilities for network exfiltration or arbitrary command execution.
- Sanitization: No specific sanitization or filtering logic is prescribed for handling external content.
Audit Metadata