update-project-docs
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local project environment to perform documentation updates.
- Ingestion points: The skill instructs the agent to read
CLAUDE.mdandAGENTS.mdin the project root and to review project changes usinggit diff. - Boundary markers: There are no instructions or delimiters defined to help the agent distinguish between its instructions and potentially malicious content embedded in the documentation or project files being analyzed.
- Capability inventory: The skill requires file read capabilities to inspect the current state of the project and documentation, and file write capabilities to apply updates to the documentation files.
- Sanitization: The skill does not specify any sanitization, validation, or filtering of the content ingested from the project files before it is processed by the agent.
Audit Metadata