implement
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process ticket information from external issue trackers, which serves as an untrusted data source. This creates a risk where malicious actors could embed instructions within tickets to influence the agent's behavior during the implementation or testing process.
- Ingestion points: Instructions in
SKILL.mdcommand the agent to fetch ticket details from an external issue tracker. - Boundary markers: There are no specified markers or delimiters to separate external ticket content from the agent's internal instructions.
- Capability inventory: The skill allows the agent to call other tools (
tdd,code-review), run shell commands for testing and typechecking, and commit changes to the repository. - Sanitization: The instructions do not define any sanitization or validation steps for the fetched ticket data.
Audit Metadata