quality-reviewer

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and configuration files. It does not include any scripts (Python, Node.js, etc.) or executable binaries, significantly reducing the attack surface.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted data (artifacts for review) which creates a surface for indirect prompt injection.
  • Ingestion points: The artifact provided by the user for review is the primary input as defined in SKILL.md.
  • Boundary markers: The instructions do not mandate the use of strict delimiters or boundary markers when the agent processes these artifacts.
  • Capability inventory: No tools are requested in the frontmatter (allowed-tools), and no code execution capabilities are present in the provided files.
  • Sanitization: There are no explicit instructions for the agent to sanitize or ignore embedded instructions within the artifacts.
  • Conclusion: As the skill lacks execution capabilities, the risk associated with this injection surface is minimal and considered a standard characteristic of the skill's intended purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 11:46 AM
Security Audit — agent-trust-hub — quality-reviewer