github-actions-finops

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses gh api and gh repo commands to interact with the GitHub API for data gathering. These are well-known and expected tools for GitHub Actions analysis.
  • [COMMAND_EXECUTION]: The SKILL.md file uses dynamic context injection (!git remote -v, !find, !gh workflow list) to provide environment context to the agent. These commands are localized to the current repository and do not involve data exfiltration or sensitive path access.
  • [SAFE]: The execution script scripts/github-actions-finops.sh implements deterministic data gathering. It uses jq for data processing and includes a fixture mechanism for offline testing, which is a security best practice for validating behavior without live network access.
  • [SAFE]: Administrative billing endpoints (/orgs/{org}/settings/billing/actions) are documented and used, but the skill includes checks for BILLING_AVAILABLE=false if the user lacks the necessary administrative permissions, preventing unauthorized access attempts or error loops.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:10 PM
Security Audit — agent-trust-hub — github-actions-finops