multi-sender-rotation
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow for processing external lead lists and lead data, which creates a surface for indirect prompt injection. If the lead data contains hidden instructions, the agent could be manipulated during the outreach process.
- Ingestion points: Lead lists and prospect data described in the pool rotation plan (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or warnings to ignore instructions embedded in the lead data.
- Capability inventory: Sending messages, managing account status, and rotating sender pools.
- Sanitization: No sanitization or validation of leads or prospect-provided content is specified.
- [NO_CODE]: The skill consists entirely of natural language instructions and configuration metadata. There are no scripts, binaries, or automated tasks that could execute local code, significantly reducing the direct attack surface.
Audit Metadata