assumption-mapper

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze external data in the form of product briefs, PRDs, or concept descriptions. This creates a surface for indirect prompt injection where a malicious document could attempt to influence the agent's behavior.
  • Ingestion points: Processes user-provided text documents (briefs, PRDs) in step 1.
  • Boundary markers: None present; there are no instructions to the model to ignore embedded commands within the analyzed documents.
  • Capability inventory: None; the skill does not use file-writing, network, or subprocess tools.
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:14 AM