crypto-quick
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external web searches, creating a surface for potential indirect prompt injection attacks if malicious content is encountered on searched pages. * Ingestion points: WebSearch results obtained during the data gathering phase in SKILL.md. * Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from following instructions embedded within external search results. * Capability inventory: The skill is limited to terminal output and does not involve file writing, network exfiltration, or code execution. * Sanitization: There is no evidence of sanitization or filtering applied to the search results before analysis.
Audit Metadata