revops
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. 1. Ingestion points: Data is ingested from external marketing context files such as
.agents/product-marketing.mdandproduct-marketing-context.md(SKILL.md). 2. Boundary markers: No delimiters or specific instructions to ignore embedded commands are present. 3. Capability inventory: The skill provides advisory templates for CRM workflows and references external tool guides, but has no direct shell or network execution capabilities. 4. Sanitization: No escaping or filtering of the external content is performed. - [SAFE]: The instructions and referenced files focus on process design, stage definitions, and standard CRM automation recipes. No suspicious command execution, exfiltration patterns, or obfuscation were identified. References to external tools like HubSpot, Salesforce, and Zapier are appropriate for the RevOps domain.
Audit Metadata