skill-reviewer

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a purely analytical process for reviewing documentation. No patterns related to command execution, data exfiltration, or malicious persistence were identified.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted content from external SKILL.md files, creating a potential surface for indirect prompt injection.
  • Ingestion points: Processes file content or markdown text provided via the user or identified in the local filesystem (e.g., SKILL.md files).
  • Boundary markers: Absent. The instructions do not provide explicit delimiters or instructions for the agent to ignore commands potentially embedded within the target files.
  • Capability inventory: The skill utilizes standard conversational and text-processing capabilities. No high-risk tools such as network access or shell execution are invoked.
  • Sanitization: Absent. The target content is processed directly as part of the review task.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 11:49 PM
Security Audit — agent-trust-hub — skill-reviewer