sales-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for interacting with external data sources which represents a potential attack surface for indirect prompt injection. \n
- Ingestion points: SKILL.md (Section 4) mentions handling web content and external data via BrowserOS. \n
- Boundary markers: Explicit instructions are provided to treat external data as hostile and maintain security boundaries. \n
- Capability inventory: The skill references the ExecutionProxy Interface for terminal actions (e.g., rtk npm test) and MemoryStore Interface for file writes. \n
- Sanitization: The protocol mandates redacting secrets and PII from context before sharing with subagents.
Audit Metadata