api-contract-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill's design involves processing untrusted external data, which introduces a surface for indirect prompt injection attacks where malicious instructions hidden in analyzed code could influence agent behavior.
- Ingestion points: The agent reads untrusted code diffs and file contents using the
Read,Grep, andGlobtools as specified in the skill configuration. - Boundary markers: The prompt does not provide explicit markers or instructions to isolate the analyzed code or to ignore potential instructions embedded within the untrusted input.
- Capability inventory: The agent is permitted to use the
Bashtool, which increases the potential impact if the agent were to follow instructions found within a malicious diff. - Sanitization: No validation or sanitization of the input code is specified before it is processed by the agent.
- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML metadata. It contains no executable scripts, compiled binaries, or automated shell commands, which limits the direct risk of the skill itself performing malicious actions.
Audit Metadata