ask-questions-if-underspecified

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes arbitrary user input within a high-privilege context.
  • Ingestion points: User feature requests and descriptions of requirements.
  • Boundary markers: The instructions do not define boundary markers or delimiters to isolate user input from the system's execution logic.
  • Capability inventory: The skill utilizes Bash, Read, and Write tools, creating a significant impact surface.
  • Sanitization: There is no evidence of input validation, filtering, or sanitization of the provided user requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:19 AM