implement
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (issue trackers) which presents a theoretical attack surface if those tickets contain malicious instructions.
- Ingestion points: Ticket content and specifications are fetched from an external issue tracker based on user-provided references (SKILL.md).
- Boundary markers: The instructions do not specify delimiters or ignore-instruction warnings for the external content.
- Capability inventory: The skill has the ability to write code, execute shell commands for testing/typechecking, and commit changes to the repository (SKILL.md).
- Sanitization: No explicit sanitization or validation of the fetched ticket content is defined.
Audit Metadata