skills/vudovn/ag-kit/plan-writing/Gen Agent Trust Hub

plan-writing

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface. The skill instructions guide the agent to generate project plan files in the project root using user-provided task descriptions and filenames.
  • Ingestion points: User input is used to derive the {task-slug} filename and markdown plan content in SKILL.md.
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore instructions within the user-provided content.
  • Capability inventory: Access to Read, Glob, and Grep tools, combined with instructions to write markdown files to the project root.
  • Sanitization: No sanitization or validation is required for the user-derived file names or content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:59 PM
Security Audit — agent-trust-hub — plan-writing