plan-as-contract

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Prompt Injection (SAFE): The instructions are benign and focus on operational safety and user approval gates.
  • No Code (SAFE): No executable scripts or binary files are included with this skill.
  • Indirect Prompt Injection (LOW): The skill interacts with untrusted data from the repository, creating a potential surface for injection.
  • Ingestion points: Repository files accessed via ReadFileSearch(*).
  • Boundary markers: None present in the instructions.
  • Capability inventory: Restricted to ReadFileSearch(*); no write, network, or execution tools are available to the skill.
  • Sanitization: No sanitization of file content is defined. The risk is minimized by the lack of powerful tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 11:21 AM