anti-slop
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external content in the form of user-provided or project-based TypeScript and JavaScript code.
- Ingestion points: Reads code blocks from user prompts or project files to identify and fix 'AI slop' patterns.
- Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from obeying malicious instructions embedded within the code being cleaned.
- Capability inventory: The skill is intended for use with AI agents that possess file system read/write capabilities and terminal access to perform code refactors.
- Sanitization: There are no explicit validation or sanitization steps defined to verify the safety of the input code before it is analyzed and modified.
Audit Metadata