diy-project-plan

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill incorporates untrusted data into its processing flow, creating a vulnerability surface. \n
  • Ingestion points: The {user_provided_details} and {project_name} variables in prompts/planning.md ingest raw user input. \n
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the prompt templates. \n
  • Capability inventory: The skill is capable of writing markdown files to the local filesystem (~/projects/diy/) as noted in the CHANGELOG.md. \n
  • Sanitization: No sanitization or validation of user-provided input is performed before interpolation. \n- [Data Exposure] (SAFE): The skill reads from ~/.config/diy-projects/tools.json and writes to ~/projects/diy/. These are skill-specific paths and do not involve sensitive system credentials or private keys. \n- [No Code] (SAFE): The provided skill contains prompt templates and data files but no executable scripts (e.g., Python or JavaScript), reducing the risk of direct malicious code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:44 PM