curviate-premium
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external LinkedIn profiles and search results, which can contain hidden instructions intended to influence the agent's behavior.
- Ingestion points: Profile data, search parameters, and resumes fetched via Sales Navigator and Recruiter commands (SKILL.md).
- Boundary markers: There are no explicit instructions for using delimiters to separate untrusted LinkedIn data from the agent's system prompts.
- Capability inventory: The skill can perform high-impact actions including sending messages, saving candidates, and publishing job postings that spend real money (SKILL.md).
- Sanitization: No content filtering or sanitization steps are documented for the data received from LinkedIn.
- [EXTERNAL_DOWNLOADS]: The skill instructions require the installation of the Curviate CLI from a public package registry.
- Evidence: npm install -g @curviate/cli (SKILL.md).
Audit Metadata