remove-ai-slop
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run development commands, build scripts, and test suites found within the audited repository. This is a core part of the automated audit and verification workflow and is considered standard behavior for this use case.
- [PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection because it reads and processes the entire contents of a local repository.
- Ingestion points: Phase 1 involves reading README files, design documentation, and the full source code inventory (via
ripgrep). - Boundary markers: There are no instructions for the agent to use delimiters or to ignore potential instructions embedded in the audited data.
- Capability inventory: The skill can write to files (Phase 8) and execute shell commands (Phase 9).
- Sanitization: No validation or sanitization of the audited content is specified.
Audit Metadata