api-design

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is intended to be used for reviewing pull requests, which requires the agent to ingest and analyze untrusted external data (code changes, comments, and metadata). This presents a vulnerability surface where a malicious contributor could attempt to influence the agent's judgment or instructions through content embedded in the PR.
  • Ingestion points: Pull request content, code diffs, and developer comments processed during review (SKILL.md).
  • Boundary markers: The skill lacks explicit instructions or delimiters to help the agent distinguish between its primary safety instructions and potentially malicious instructions embedded in the PR data.
  • Capability inventory: While this specific skill file does not define executable scripts or network-enabled tools, it directs the agent's reasoning process during review.
  • Sanitization: No evidence of sanitization or filtering of the external PR data is provided in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:31 AM
Security Audit — agent-trust-hub — api-design