onequery-pr-body

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use git and gh (GitHub CLI) for repository and pull request management. These commands are necessary for the skill's stated purpose and are used in a standard manner.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill explicitly warns the agent to avoid including absolute paths from the local disk in the PR body. This is a best-practice instruction that protects against accidental leakage of sensitive local system information.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with existing pull request bodies and conversation context. While this creates a surface for indirect prompt injection, it is a functional requirement for synthesizing PR descriptions and lacks high-risk capabilities like dynamic code evaluation.
  • [SAFE]: No obfuscation, malicious persistence mechanisms, or unauthorized network operations were detected. All external resources and repositories are consistent with the author's identity.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:46 AM
Security Audit — agent-trust-hub — onequery-pr-body