hermes-traffic-guardian

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The SKILL.md file contains a verification script that downloads release artifacts, including checksums, signatures, and archives, from the vendor's GitHub repository (github.com/prompt-security/clawsec) to ensure the integrity of standalone installations.- [COMMAND_EXECUTION]: The provided verification script utilizes standard command-line utilities such as curl, openssl, jq, and shasum. These tools are used solely for cryptographic verification of downloaded files and are not used to execute untrusted remote code.- [SAFE]: This skill currently functions as a technical specification and does not ship with a functional proxy or runtime monitoring implementation. The design documents emphasize safety requirements such as opt-in only operation, secret redaction, and no automatic system-wide modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 10:42 AM
Security Audit — agent-trust-hub — hermes-traffic-guardian