codepulse-loc
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 context, which exposes the agent to instructions embedded in source files that could influence the final report.
- Ingestion points: The entire codebase context (SKILL.md).
- Boundary markers: There are no specific instructions or delimiters provided to ensure the agent ignores or sanitizes instructions found within the code files.
- Capability inventory: The skill includes the ability to count lines, categorize code by language, and write an HTML report to the local file system (SKILL.md).
- Sanitization: No explicit sanitization or escaping mechanisms for external code content are defined in the instructions.
Audit Metadata