codepulse-quality
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the entire codebase as input, creating an attack surface where malicious comments or data in the source files could influence the agent's analysis, grading, or report content. \n
- Ingestion points: The entire codebase is used as context for the health check instructions in SKILL.md. \n
- Boundary markers: Absent. There are no instructions to delimit or ignore potentially malicious content within the codebase. \n
- Capability inventory: The skill performs file-write operations to the local filesystem (codepulse-quality/reports/). \n
- Sanitization: Absent. The skill does not specify sanitization or validation of the codebase content before processing.
Audit Metadata