partnership-collaboration-inquiry
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is entirely descriptive and instructional, focusing on text-based communication.
- [DATA_EXPOSURE]: The skill contains references to public social media profiles and business websites (e.g., Matt Pocock, Kent C. Dodds, Total TypeScript). These are used as legitimate contact targets for partnership inquiries and do not constitute sensitive data exposure.
- [PROMPT_INJECTION]: The instructions in SKILL.md provide negative constraints (e.g., 'Don't introduce policy details') to ensure accuracy, which is a benign use of instruction overriding rather than a malicious bypass attempt.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted external inquiries (partnership requests), its capabilities are limited to text responses without tool execution, making the risk of indirect injection negligible in this context.
Audit Metadata