tailrocks-seed-roadmap
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill serves as a tool for ingesting 'untrusted evidence' (security findings and plans), which represents an attack surface for indirect prompt injection. The instructions include explicit defensive logic, mandating that the agent treat input text as untrusted data, refuse instructions embedded within the findings, and maintain strict boundaries to prevent unauthorized actions.
Audit Metadata