task-generation

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from requirement files that may contain untrusted data.
  • Ingestion points: The skill reads content from .ai/[feature-name]/prp.md to generate tasks.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions embedded within the PRP file.
  • Capability inventory: The agent has the ability to write files to the local disk and execute git commands.
  • Sanitization: The skill does not implement sanitization or validation logic for the content read from the requirement files.
  • [COMMAND_EXECUTION]: The skill instructions include automated version control operations.
  • Evidence: Step 10 instructs the agent to stage and commit the generated task list using a predefined commit message template.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 06:04 PM