skills/brijr/skills/what-shipped/Gen Agent Trust Hub

what-shipped

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill demonstrates a strong security posture by including explicit instructions to avoid the exposure of secrets, sensitive data, and private tokens during the summarization process.
  • [COMMAND_EXECUTION]: The skill uses standard development tools including git and gh (GitHub CLI) to retrieve repository state, commit history, and Pull Request metadata. These operations are limited to the repository context and align with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill processes untrusted content from Pull Request bodies and commit messages, which represents a surface for indirect prompt injection.
  • Ingestion points: Untrusted data is ingested from GitHub PRs and Git history as specified in the workflow of SKILL.md.
  • Boundary markers: The skill does not define specific delimiters to isolate summarized content from the agent's instructions.
  • Capability inventory: Tool usage is restricted to git, gh, and well-known deployment platform CLIs (Vercel, Render, Cloudflare); no dynamic execution or unsafe interpolation is present.
  • Sanitization: The skill contains explicit logic in Step 6 of SKILL.md to identify and omit sensitive information including secrets, private URLs, and customer data from the final output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 02:01 PM
Security Audit — agent-trust-hub — what-shipped