outbound-prospecting-engine
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow that ingests untrusted data from external platforms to influence automated actions, creating an indirect prompt injection surface. 1. Ingestion points: Data is pulled from external job postings and LinkedIn content via specialized sub-skills (SKILL.md). 2. Boundary markers: The playbook does not specify explicit delimiters or instructions to ignore embedded instructions in external data. 3. Capability inventory: The system has the capability to generate personalized emails and launch automated outreach campaigns (SKILL.md). 4. Sanitization: The risk is mitigated by explicit 'Human Checkpoints' required after lead qualification and email generation, ensuring human oversight before external communication occurs.
- [SAFE]: The skill is a high-level orchestration playbook that defines a logic flow using other existing skills; it contains no standalone scripts, hidden code, or unauthorized network exfiltration logic.
Audit Metadata