outbound-prospecting-engine
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a process orchestrator (playbook) and does not contain executable code, obfuscated content, or direct instructions to bypass security filters.
- [PROMPT_INJECTION]: The skill defines a workflow for indirect prompt injection by ingesting untrusted data from external sources to generate personalized email sequences.
- Ingestion points: Signal detection steps involve reading job postings, LinkedIn posts, and funding announcements (SKILL.md).
- Boundary markers: The playbook does not specify the use of delimiters or 'ignore' instructions for the external content.
- Capability inventory: The workflow utilizes capabilities for sending emails (
agentmail) and configuring campaign tools (setup-outreach-campaign). - Sanitization: No sanitization or validation logic is mentioned for the external data before it is interpolated into prompts for email generation.
Audit Metadata