co-marketing
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on business strategy and partner identification. It contains a directive to read local files such as
.agents/product-marketing.mdto gather context about the user's product. This is a standard workspace-integration pattern for context-aware agents and does not involve any dangerous sinks such as shell execution or file-writing based on that data. - [SAFE]: All external references within the skill point to well-known technology services (Crossbeam, Introw, PartnerStack) or internal documentation paths. No obfuscated code, unauthorized remote downloads, or credential harvesting patterns were identified.
- [SAFE]: The evaluation prompts and expected outputs in
evals.jsonare consistent with the skill's stated purpose and do not contain malicious payloads or injection attempts.
Audit Metadata