ccdawn-project-review

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly limited to read-only operations for repository analysis. It explicitly defines that it does not edit files, move branches, or modify indices, which minimizes the risk of accidental or malicious data modification.
  • [COMMAND_EXECUTION]: The skill suggests using standard, safe, read-only commands such as git status, git log, and rg (ripgrep) to gather project information. These operations are well-scoped to the skill's purpose of code and project health review.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading external data from the repository (e.g., code comments, README files). While this is an ingestion point for untrusted data, the risk is mitigated by the skill's read-only nature and structured output format.
  • Ingestion points: Local repository files, git logs, and configuration files via rg and git commands.
  • Boundary markers: The skill uses a highly structured 'Output Contract' to organize findings, although specific delimiters for the ingested content are not defined.
  • Capability inventory: The skill is limited to read-only CLI tools (git, rg). No network access or file-write capabilities are requested or used.
  • Sanitization: Not explicitly mentioned, but the output is restricted to Chinese-first reports and structured technical findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 09:31 AM
Security Audit — agent-trust-hub — ccdawn-project-review