cc-quality-practices
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of process documentation and checklists. It does not perform network operations, access sensitive credentials, or execute arbitrary system commands. All file references are to internal documentation within the skill's own directory or the shared plugin root.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to evaluate external code or project descriptions, which constitutes a potential ingestion point for indirect prompt injection. However, the risk is minimal as the skill lacks capabilities that could be exploited by malicious input.\n
- Ingestion points: The
CHECKERmode inSKILL.mdingests user-provided code or process data for evaluation.\n - Boundary markers: The instructions do not define specific delimiters for the input data to isolate it from instructions.\n
- Capability inventory: The skill utilizes the
Readtool for internal documentation and chains to other informational skills; it has no file-write, network, or shell execution capabilities.\n - Sanitization: No explicit instructions are provided to sanitize input or ignore embedded instructions within the code being checked.
Audit Metadata