update-readme
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate file system and repository management tasks. It uses tools like
Read,Write,Edit, andGlobto manage documentation andBash(git:*)to check project history. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from the repository to generate documentation.
- Ingestion points: Step 1 (Survey the project) instructs the agent to read all skill/module directories,
SKILL.mdfiles, and existing README files. - Boundary markers: No explicit delimiters or boundary markers are defined for the data read from project files.
- Capability inventory: The skill has
Write,Edit, andBash(git:*)capabilities to modify the repository. - Sanitization: No explicit sanitization or filtering of the ingested content is specified before drafting new README files.
- Note: This behavior is inherent to the primary function of a documentation tool and is considered acceptable risk given the intended use case.
Audit Metadata