skills/imankulov/skills/draft/Gen Agent Trust Hub

draft

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the system's temporary directory (/tmp/) to store generated drafts, which is a standard and safe practice for transient data.
  • [SAFE]: The workflow involves opening generated markdown files in the VS Code editor using the code command, facilitating user review and editing without suspicious flags.
  • [SAFE]: Indirect Prompt Injection Surface Analysis:
  • Ingestion points: User requests for drafting various types of prose as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters for the draft content.
  • Capability inventory: The agent writes to the file system (/tmp/) and executes the code command.
  • Sanitization: The skill does not explicitly describe sanitization steps for user-provided input, which is a standard surface for drafting tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 12:27 PM