de-sloppify
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by scanning user-provided source code files and modifying them based on the results. This ingest-and-edit pattern creates a surface where adversarial code could potentially influence the agent's cleanup decisions, although the risk is mitigated by deterministic heuristics and a required manual diff review step.
- Ingestion points: Target source files are read via the
Readtool and processed by themain.cjsscript. - Boundary markers: No explicit markers are used to separate untrusted file content from instructions in the prompt context.
- Capability inventory: File modification (Edit tool), file reading (Read tool), and shell execution (Bash tool) for git and pnpm operations.
- Sanitization: The skill uses deterministic regular expression heuristics within the
main.cjsscript to identify lines safe for removal. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
Bashtool, includinggit diffwith output redirection, local execution of themain.cjsscript, and project tools likepnpm lint:fix. It specifically references absolute Windows file paths (e.g.,C:/dev/projects/agent-studio/...) for temporary diff files and project context.
Audit Metadata