simplify
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes and modifies code within the user's workspace, which creates a surface for indirect prompt injection if the ingested code contains malicious instructions. This risk is inherent to the skill's primary purpose of stylistic refactoring. Ingestion points: User-specified code scope or current branch (SKILL.md). Boundary markers: Absent. Capability inventory: Code review and modification via agent tools. Sanitization: Absent.\n- [SAFE]: No explicit security threats such as credential exfiltration, obfuscation, or unauthorized network access were found. The skill instructions follow standard stylistic principles (e.g., Orwell's rules) and include safety directives to run existing checks and avoid changing behavior.
Audit Metadata