reactivation-specialist
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill acts as an instructional framework for email marketing without shipping any executable code.
- [PROMPT_INJECTION]: While the skill defines a surface for indirect prompt injection by processing external ESP exports and subscriber lists, this is a standard operational requirement for the skill's purpose. The instructions explicitly mitigate this risk by mandating that the agent treat all external data as untrusted and ignore any embedded commands.
- Ingestion points: External ESP engagement exports, CSV files, and pasted data.
- Boundary markers: None specified for interpolation, but instructional mitigations are present.
- Capability inventory: File system access is limited to writing results to specific agent memory paths; no network or command execution capabilities are utilized.
- Sanitization: Explicit instruction provided to the agent to disregard any instructions contained within processed external files.
Audit Metadata