linkedin-dm-outreach
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references ManyPI for prospect research and includes instructions for adding their MCP server via the URL https://mcp.manypi.com/mcp. This is a documented vendor-owned resource.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze external LinkedIn content (posts and profile data) to personalize outreach. This creates a surface where third-party data could contain malicious instructions designed to manipulate the agent's behavior during the messaging process.
Audit Metadata