clean-code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it is designed to ingest and analyze untrusted third-party code.
- Ingestion points: The skill takes code snippets or entire files as input from the user to perform refactoring and quality checks (referenced in
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters (e.g., XML tags or specific 'ignore instructions within code' headers) provided to the agent to help it distinguish between legitimate code comments and malicious instructions intended to hijack the session.
- Capability inventory: The skill does not currently define or use high-risk tools such as network access or shell command execution, which significantly limits the potential impact of a successful injection.
- Sanitization: No sanitization or pre-processing steps are mentioned to filter out potential injection patterns from the input before the LLM processes it.
Audit Metadata