crm-segmentation-planner
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill files consist of markdown instructions, reference documentation, and a plugin manifest, with no evidence of executable code, obfuscation, or dangerous system commands.
- [SAFE]: All external references target the author's legitimate website (infloq.com) for additional context and examples, which is a safe and expected behavior for this skill.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection through its processing of user-supplied CRM data and lifecycle goals. However, the risk is assessed as safe because the agent's capabilities are limited to planning and documentation tasks using standard Read and Write tools, with no access to sensitive system resources or external network exfiltration. Ingestion points: User-provided lifecycle goals and data fields in SKILL.md. Boundary markers: Absent. Capability inventory: Limited to Read and Write operations for documentation. Sanitization: None identified.
Audit Metadata