remove-ai-slops
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes source code from branch diffs that may contain malicious instructions.
- Ingestion points: Source code content and file lists are ingested through
git diffand file reads in Phases 1 and 4. - Boundary markers: The skill lacks explicit delimiters to separate untrusted code from instructions.
- Capability inventory: The agent can modify files using the
Edittool, execute shell commands through project runners, and orchestrate sub-agents. - Sanitization: No sanitization is performed on the ingested code before analysis.
- [COMMAND_EXECUTION]: The skill performs local command execution and manages dynamic script execution.
- It uses
git,awk, andwcfor repository analysis and file metrics. - It executes local project tools for testing, linting, and type-checking.
- It generates and runs regression tests in Phase 2 to verify that cleanup operations do not alter existing program behavior.
Audit Metadata