champion-move-outreach
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard B2B sales automation workflow. It operates within the expected scope of sales intelligence and outreach tools.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface (Category 8). The skill processes untrusted data from web searches and social media profiles during company research and job change detection.
- Ingestion points: External data enters the workflow via web search tools in Step 1 and Step 2 of
SKILL.md. - Boundary markers: Absent. The skill does not define specific delimiters to isolate external text from agent instructions.
- Capability inventory: The skill has capabilities for web search, contact finding, and email drafting. It hands off to other skills for final outreach execution.
- Sanitization: No explicit sanitization or filtering of external content is performed. The risk is mitigated by the design of the workflow, which includes mandatory human review checkpoints before any outreach is finalized or sent.
- [DATA_EXFILTRATION]: The skill processes personal identifiable information (PII) such as names, titles, and email addresses. This data handling is consistent with the skill's stated purpose of sales outreach and involves transferring data to user-configured CRM and engagement tools.
Audit Metadata