capture-idea

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by using user-supplied idea text to guide codebase searches and documentation creation.
  • Ingestion points: Raw idea text enters via the argument-hint or Step 1.
  • Boundary markers: Absent; user input is not delimited in templates or search queries.
  • Capability inventory: Performs glob/grep searches and file reads/writes across the codebase.
  • Sanitization: Absent; no input validation is performed on the user-provided idea text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:16 AM