flow-governance-review

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill implementation uses npm exec to fetch and execute the @tiangong-lca/cli package from the public npm registry. This is the intended delivery mechanism for the vendor's command-line tools and originates from the author's own namespace.
  • [COMMAND_EXECUTION]: The script scripts/run-flow-governance-review.mjs facilitates the execution of various tiangong CLI subcommands. These operations are strictly limited to the documented flow governance, remediation, and repair workflows.
  • [CREDENTIALS_UNSAFE]: The skill identifies and documents the use of environment variables like TIANGONG_LCA_API_KEY for authentication. The source code does not contain hardcoded secrets, and standard secret management practices (using environment variables) are followed.
  • [SAFE]: A review of the instructions and scripts shows no evidence of prompt injection, persistence mechanisms, or multi-layer obfuscation. The skill's behavior matches its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:57 AM
Security Audit — agent-trust-hub — flow-governance-review