planning-with-files

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill defines a workflow for storing and reading research data. 1. Ingestion points: notes.md and task_plan.md. 2. Boundary markers: Absent. 3. Capability inventory: Standard file operations (Read, Write, Edit). 4. Sanitization: Absent. The pattern is intended for task management and contains no malicious instructions or automated execution of untrusted data.
  • No Code (SAFE): The skill is composed of markdown documentation and templates. No executable scripts, binaries, or automated command-line patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:47 PM