tldr
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill focuses on summarizing task artifacts and logs, which are external data sources that could potentially contain malicious instructions.
- Ingestion points: Task results, build logs, and workflow artifacts mentioned in SKILL.md.
- Boundary markers: Not specified in the skill instructions.
- Capability inventory: The skill does not define or use any tools or scripts.
- Sanitization: The skill includes a security instruction to redact secrets, tokens, and passwords from the summary.
Audit Metadata