workflow-pr

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository artifacts which could potentially embed instructions to bias the agent's output.
  • Ingestion points: Inspects base-to-head diffs, commit messages, and repository templates in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions within the ingested data.
  • Capability inventory: The skill is capable of creating or updating remote pull requests as noted in SKILL.md.
  • Sanitization: No explicit sanitization or validation of the ingested code or text content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 04:08 PM
Security Audit — agent-trust-hub — workflow-pr