implement
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon implementation specifications and tickets, which creates a surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data from a "spec or set of tickets" described in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters provided to help the agent differentiate between the workflow instructions and the content of the specifications.
- Capability inventory: The skill allows the agent to run typechecking, execute test suites, and commit work to the current branch, which could be exploited if the input data contains malicious instructions.
- Sanitization: No sanitization, validation, or filtering of the input specifications is mentioned.
Audit Metadata