update-project-docs
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the project's codebase to generate documentation, which could allow instructions embedded in comments or metadata to influence the agent's behavior during the generation process.
- Ingestion points: The skill reads various project files including source code,
package.json,.env.example,openapi.yaml, and infrastructure files (Dockerfile) as documented indocs-sync.mdandcodemaps.md. - Boundary markers: The instructions mandate wrapping generated content with
<!-- AUTO-GENERATED -->markers, which helps identify AI-produced text but does not provide a security boundary against adversarial content in the source data. - Capability inventory: The skill possesses the ability to read project files and write to the
docs/and.reports/directories. - Sanitization: There is no mention of sanitizing or escaping the text extracted from source files before it is interpolated into the generated documentation or codemaps.
Audit Metadata