explorer

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists exclusively of instructional prompts and metadata with no executable code or binary components.- [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Processes local codebase files and symbols.
  • Boundary markers: Absent; no delimiters are defined for scanned content.
  • Capability inventory: No subprocess calls, network access, or file-write capabilities exist; the write and edit tools are explicitly disabled in the frontmatter.
  • Sanitization: None detected; the skill relies on the agent's internal safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:18 AM
Security Audit — agent-trust-hub — explorer