skills/cloudvoyant/codevoyant/cz/Gen Agent Trust Hub

cz

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the project's commit history and configuration files to calculate versioning. While commit messages are external data that could contain instructions, the skill's purpose is limited to version prediction.
  • Ingestion points: Reads git commit history and project configuration files including pyproject.toml, package.json, and .cz.toml (SKILL.md).
  • Boundary markers: None explicitly defined to separate commit data from instructions.
  • Capability inventory: Executes cz and git commands for metadata extraction (SKILL.md).
  • Sanitization: No specific filtering or sanitization of commit messages or configuration values is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:12 AM
Security Audit — agent-trust-hub — cz