wendy-device-interop

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown documentation and reference guides. No executable code, scripts, or automated tools are included.
  • [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were found.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were identified. The external reference to Linear is a legitimate vendor resource.
  • [OBFUSCATION]: No encoded content, zero-width characters, or homoglyph attacks were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a secure protocol for handling external data through the 'postbox' system. It specifies mandatory verification steps including signature checks, hash-chain validation, and high-water mark enforcement to prevent malicious data from affecting the device state.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:04 PM
Security Audit — agent-trust-hub — wendy-device-interop