implement
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and act upon untrusted data from external specifications or tickets.
- Ingestion points: The skill body in
SKILL.mdinstructs the agent to "Implement the work described by the user in the spec or tickets." - Boundary markers: The instructions do not define boundary markers (such as XML tags or delimiters) to separate instructions from the data, nor do they advise the agent to ignore instructions embedded within the specifications.
- Capability inventory: The agent is granted capabilities to write code, execute typechecking and test suites, and perform version control commits ("Commit your work to the current branch").
- Sanitization: No sanitization, validation, or human-in-the-loop review steps are specified for the incoming specification data before implementation begins.
Audit Metadata