call-prep
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through search and scraping capabilities via sandbase_run (SKILL.md). Boundary markers are present in the form of instructions to clearly mark unverified content. Capabilities include external data retrieval using vendor-defined tools (references/sandbase-api-map.md). No specific sanitization methods for the external data are described.
- [SAFE]: No malicious code or patterns were identified. The skill utilizes vendor-specific tools for its primary function and implements safety gates such as user confirmation for all paid external calls.
Audit Metadata