pr-description

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted sources within the repository context.
  • Ingestion points: Commit messages, branch names, and repository templates such as .github/PULL_REQUEST_TEMPLATE.md.
  • Boundary markers: The skill instructs the agent to output the final description within a fenced markdown block to separate it from other instructions.
  • Capability inventory: The skill is restricted to file reading and git diffing; it explicitly prohibits modifications such as writes, commits, or edits to tracked files.
  • Sanitization: No explicit sanitization or filtering of input content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 02:27 PM
Security Audit — agent-trust-hub — pr-description