ai-writing-detox
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The skill consists of linguistic constraints and does not contain instructions that attempt to override system safety protocols, bypass filters, or extract system prompts.\n- [Data Exposure & Exfiltration] (SAFE): There are no patterns involving sensitive file paths (e.g., SSH keys, environment variables) or network operations (e.g., curl, fetch) to transmit data externally.\n- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No scripts, package managers (pip, npm), or remote execution patterns were found. The skill is entirely declarative markdown.\n- [Indirect Prompt Injection] (LOW): The skill is designed to process external content (articles/documentation). 1. Ingestion points: User-provided text content. 2. Boundary markers: None specified. 3. Capability inventory: Natural language output only; no subprocess calls, file-write operations, or network access. 4. Sanitization: None. While the injection surface is present, the risk is low due to the lack of dangerous capabilities.
Audit Metadata