interactive-requirements-gathering

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by design. It encourages the agent to accept arbitrary user input and treat it as the authoritative source for subsequent generation tasks.
  • Ingestion points: User input provided via the 'Type your own answer' option (Option D) and the interactive feedback loop as defined in SKILL.md.
  • Boundary markers: Absent. The instructions do not specify the use of XML tags, delimiters, or system-level instructions to ignore potential commands embedded within user-provided text.
  • Capability inventory: The agent has access to Read, Write, Edit, and AskUserQuestion tools, which could be misused if the agent obeys instructions injected through user responses.
  • Sanitization: Absent. The skill's 'Iron Laws' and workflow instructions mandate using the user's input directly for generation without validation or escaping mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:29 PM