implement
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from external issue trackers and user-provided specifications, which serves as an injection vector for instructions that could manipulate the agent's implementation and testing logic.
- Ingestion points: Ticket references fetched from an issue tracker and user-provided specs (SKILL.md).
- Boundary markers: None identified in the instructions to separate untrusted data from system logic.
- Capability inventory: The agent is authorized to call other skills ("tdd", "code-review"), execute shell commands for typechecking and testing, and perform git commits (SKILL.md).
- Sanitization: There are no explicit instructions to sanitize or validate the content fetched from the issue tracker before processing it.
Audit Metadata