skills/kevinslin/skills/audit/Gen Agent Trust Hub

audit

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill defines a benign workflow for code quality analysis using search and read tools like 'rg'. No unauthorized data access, network connections, or persistence mechanisms were detected.
  • [NO_CODE]: The skill consists entirely of markdown instructions and does not contain any executable scripts, binary files, or external package dependencies.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted repository content, including codebase files and local agent guidance (e.g., AGENTS.md). This creates a surface for indirect prompt injection where embedded instructions could attempt to influence the agent's audit findings. This risk is inherent to the tool's primary function.
  • Ingestion points: Repository file reads and 'rg' search results in 'references/slop.md'.
  • Boundary markers: None specified in instructions.
  • Capability inventory: File system read access (standard).
  • Sanitization: None specified in instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 02:25 PM
Security Audit — agent-trust-hub — audit