implement
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content from specifications or tickets which creates a surface for indirect instructions to potentially influence agent behavior.
- Ingestion points: The skill ingests work descriptions from user-provided 'specs' or 'tickets' as described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill text.
- Capability inventory: The skill is instructed to perform command execution for typechecking, running test suites, and committing work to a repository branch.
- Sanitization: No evidence of input validation or sanitization routines is provided for the external content.
Audit Metadata