decomposing-project-tasks

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes Node.js scripts (e.g., scripts/analyze-requirements.js) to process user data and generate structured task lists.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted assignment files.
  • Ingestion points: Assignment text files are read by scripts/analyze-requirements.js for requirement extraction.
  • Boundary markers: There are no explicit delimiters used in the scripts or instructions to separate untrusted content from the agent's internal logic.
  • Capability inventory: The skill possesses file system read/write access and the ability to execute Node.js commands.
  • Sanitization: No input validation or escaping is performed on the content extracted from external files before it is processed or presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:44 PM
Security Audit — agent-trust-hub — decomposing-project-tasks