ai-slop-cleaner
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for running test suites and managing git state (e.g.,
git checkout -- .). These capabilities are essential for the defined 'Regression-Safe Workflow' but grant the skill shell access. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify untrusted external data in the form of project code files, which creates a potential vector for indirect prompt injection.
- Ingestion points: The skill reads and evaluates code across the entire codebase (TypeScript, Python, Go, etc.).
- Boundary markers: The instructions mention specific markers such as
// KEEPor// intentionalto protect code blocks from cleanup, though these are logical rather than security-focused delimiters. - Capability inventory: The skill utilizes shell command execution (tests, git) and file system write access to perform its duties.
- Sanitization: There is no mention of sanitizing or escaping the content of the processed files before they are interpreted by the agent.
Audit Metadata