gh-board-sync

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill exclusively uses the official GitHub CLI (gh) to interact with repositories and project boards. All network traffic is directed to GitHub's infrastructure via the user's authenticated CLI session.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub Pull Request descriptions. It mitigates potential injection risks by explicitly instructing the agent to treat this data as untrusted and by using non-executable regex patterns to extract specific issue references.
  • [COMMAND_EXECUTION]: Command execution is limited to the GitHub CLI and the local report script. Arguments are handled as arrays in execFileSync, preventing shell injection vulnerabilities.
  • [SAFE]: No evidence of obfuscation, hardcoded credentials, exfiltration, or persistence mechanisms was found. The skill follows the principle of least privilege by requiring user confirmation for all mutations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 08:21 AM
Security Audit — agent-trust-hub — gh-board-sync