review-clean-code
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and analyze external codebase files, creating a vulnerability surface where malicious instructions within the reviewed code could target the agent.
- Ingestion points: The
SKILL.mdworkflow explicitly instructs the agent to scan the codebase and identify files to review. - Boundary markers: The prompt instructions do not provide specific delimiters or 'ignore' directives to help the agent distinguish between code logic and potential instructions embedded in comments or string literals.
- Capability inventory: The skill leverages the agent's existing capabilities to read the local filesystem and write structured reports (
clean-code-review.mdandclean-code-review.json). - Sanitization: There are no mechanisms defined to sanitize, escape, or validate the content of the source files before they are processed by the agent.
- [NO_CODE]: The skill package does not contain any executable scripts, binaries, or automated configuration files, consisting solely of informational markdown documents.
Audit Metadata