writing-task-briefs-and-guides
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard workflow for summarizing and reformatting user-provided text. No patterns of obfuscation, credential harvesting, or unauthorized network activity were identified.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source documentation which could contain malicious instructions. Ingestion points: Source file read in the first step of the Process. Boundary markers: None explicitly defined to distinguish source text from instructions. Capability inventory: Text generation and file writing to specific markdown and text extensions. Sanitization: None. The risk is safe because the agent's available tools are limited to text processing and file creation, preventing the execution of arbitrary commands or data exfiltration.
Audit Metadata