simplify-and-harden-ci

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted code from pull requests to perform security and quality reviews. This creates a surface for indirect prompt injection where a malicious contributor could include instructions within the code changes to manipulate the agent's review output or behavior.
  • Ingestion points: The skill specifically instructs the agent to review files changed in the pull request (SKILL.md).
  • Boundary markers: The prompt instructions do not provide explicit delimiters or boundary markers to isolate the code being analyzed from the agent's instructions.
  • Capability inventory: The skill is capable of posting structured findings as comments to the pull request and failing CI runs based on severity gates (SKILL.md).
  • Sanitization: The workflow does not describe any specific sanitization or filtering of the pull request content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill references and requires the installation of the gh-aw extension and associated GitHub Actions from the official github organization. These are trusted resources used for the skill's core automation functionality.
  • Evidence: References to github/gh-aw extensions and actions for setting up the CLI environment (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 07:00 AM
Security Audit — agent-trust-hub — simplify-and-harden-ci