known-issue-research
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests information from external sources like StackOverflow and GitHub Issues during its research phase.\n
- Ingestion points: WebSearch results used for root-cause triage and industry-wide evaluation (SKILL.md).\n
- Boundary markers: There are no explicit markers or instructions to delimit external content from the skill's operational logic.\n
- Capability inventory: The skill is designed for technical-analysis stages of code-fixing, implying the agent may have file system and execution permissions.\n
- Sanitization: No sanitization of the fetched web data is specified in the provided instructions.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install a necessary dependency from the author's own repository (
FuDesign2008/open-skills).
Audit Metadata