ai-slop-cleaner
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill describes a workflow that involves processing and executing untrusted code, creating a surface for indirect prompt injection.
- Ingestion points: The skill targets code snippets, files, or 'AI-generated slop' for refactoring and cleanup tasks (SKILL.md).
- Boundary markers: No specific delimiters or instructions are provided to help the agent distinguish between its own operational instructions and potentially malicious instructions embedded within the code or comments being refactored.
- Capability inventory: Step 5 ('Run quality gates') instructs the agent to execute regression tests, unit/integration tests, and linting/typechecking tools, which require the execution of code in the agent's environment.
- Sanitization: The instructions do not mention any sanitization of the input code or the use of sandboxed environments for performing the required test executions.
Audit Metadata