one-earth

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely comprised of markdown documentation. It does not include any scripts, commands, or network calls.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill processes user-supplied manuscripts.
  • Boundary markers: The instructions do not define explicit delimiters for untrusted input.
  • Capability inventory: No active capabilities (such as shell commands or network access) are defined or utilized.
  • Sanitization: There is no evidence of input sanitization, but the lack of capabilities renders the surface safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 11:33 AM
Security Audit — agent-trust-hub — one-earth