idea-os

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes WebSearch and WebFetch tools to gather market data and competitor information from the internet. This is a functional requirement for the 'Research' phase of the product pipeline and uses standard platform capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by processing data from external websites.
  • Ingestion points: External data enters the agent context via WebSearch and WebFetch during Phase 3 (Research).
  • Boundary markers: The instructions do not specify explicit delimiters or 'ignore' warnings for the fetched content, though it requires assumptions to be flagged.
  • Capability inventory: The skill writes several files to the local workspace (questions.md, research.md, PRD.md, plan.md) and uses search tools.
  • Sanitization: No explicit sanitization or filtering of external content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 08:54 AM
Security Audit — agent-trust-hub — idea-os