requirements-doc-gen

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided 'rough descriptions' and existing documents. It lacks explicit safety boundaries or instructions to disregard potential commands embedded within these external inputs.
  • Ingestion points: Processes user-provided text and uploaded documents in SKILL.md (Scenario 1 Step 1 and Scenario 2 Step 1).
  • Boundary markers: Absent; there are no instructions to delimit user data or ignore embedded prompts.
  • Capability inventory: Utilizes web_search to fetch external information (Scenario 1 Step 6).
  • Sanitization: Absent; no validation or filtering is applied to the content of processed documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 03:03 AM