deslop
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior detected. The skill provides guidelines for code style consistency without using external scripts or network access.
- [INDIRECT_PROMPT_INJECTION]: The skill operates on external data (code diffs), which presents a potential surface for indirect prompt injection. A malicious snippet in a pull request could attempt to influence the agent's editing behavior.
- Ingestion points: Code diffs against the main branch.
- Boundary markers: Missing delimiters to separate processed code from agent instructions.
- Capability inventory: Filesystem write access (implied by code removal task).
- Sanitization: No input sanitization or validation of the code being processed.
Audit Metadata