github-star-manager
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from articles, screenshots, and repository READMEs, which creates a surface for indirect prompt injection.\n
- Ingestion points: Content is retrieved via WebFetch for articles, image analysis for screenshots, and the GitHub API for project READMEs.\n
- Boundary markers: The AI prompt construction in the summarization module does not use specific delimiters or instructions to distinguish between system instructions and untrusted external data.\n
- Capability inventory: The skill has the capability to perform repository actions (star/unstar) via API/CLI and write results to the file system.\n
- Sanitization: No specific sanitization or escaping is performed on the ingested content before AI processing.
Audit Metadata