edit-article
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are limited to text processing and restructuring. No dangerous capabilities such as file system access, network operations, or command execution were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided articles which represents a data ingestion surface. 1. Ingestion points: Article text provided by the user for editing in SKILL.md. 2. Boundary markers: No explicit instructions to the agent to ignore instructions embedded within the article text. 3. Capability inventory: No capabilities (tools, shell, network) are requested or used. 4. Sanitization: No input sanitization is performed.
Audit Metadata