de-AI-writing

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external user-provided text, creating a potential surface for indirect prompt injection. However, it implements security best practices by including a 'Safety Boundary' section that explicitly instructs the agent to treat all target text, file contents, links, and citations as data rather than instructions.
  • [NO_CODE]: The skill is composed entirely of Markdown instructions and local reference files. It does not utilize any executable scripts, third-party package dependencies, or remote code patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:54 AM
Security Audit — agent-trust-hub — de-AI-writing