loop-on-ci

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill uses the official GitHub CLI (gh) to interact with a repository's pull request checks and logs. All network activity is directed toward GitHub, which is a trusted and well-known service.
  • [COMMAND_EXECUTION]: The skill uses standard shell commands (gh pr view, gh pr checks, gh run view) to perform CI monitoring tasks. These commands are legitimate and consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill processes CI logs, which are external data. While this represents a potential surface for indirect prompt injection, it is a standard requirement for CI automation tools and no exploit patterns were observed. The skill instructs the agent to diagnose failures, which is typical behavior for a developer-oriented skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 09:17 AM
Security Audit — agent-trust-hub — loop-on-ci