implement
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources like user requests and specifications, which serves as a vector for indirect prompt injection.
- Ingestion points: Worker scope is defined by external briefs, specifications, and tickets in SKILL.md.
- Boundary markers: Absent; the skill lacks delimiters or instructions to ignore instructions embedded in tickets.
- Capability inventory: SKILL.md authorizes the agent to edit files, execute verification tools (/tdd), and use version control (commit, pr).
- Sanitization: Absent; there is no mention of sanitization or validation for external content before implementation.
Audit Metadata