implement
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted data from a "spec or set of tickets", which may contain malicious instructions designed to influence agent behavior.
- Ingestion points: The agent is instructed in
SKILL.mdto process work described in external specifications or tickets. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data to be processed and instructions to be followed.
- Capability inventory: The skill allows the agent to execute shell-based commands for typechecking and testing, and perform filesystem operations via
git commit. - Sanitization: No sanitization, validation, or escaping of the input specification content is mentioned.
Audit Metadata