crypto-analyze

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests untrusted data from external web sources during its discovery phase.
  • Ingestion points: The skill uses WebSearch in Phase 1 to gather data on token prices, market trends, and news from the open web.
  • Boundary markers: There are no explicit instructions to the agent to treat fetched web content as untrusted data or to ignore embedded instructions within that content.
  • Capability inventory: The skill has the ability to launch sub-agents using the Agent tool and write analysis reports to the local filesystem.
  • Sanitization: No specific sanitization or validation steps are defined for the data retrieved via WebSearch before it is processed or passed to sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 01:34 AM
Security Audit — agent-trust-hub — crypto-analyze