content-engagement
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from LinkedIn engagement (likes and comments) via the extraction tool. This external data could theoretically contain malicious instructions designed to hijack the agent's logic during lead enrichment or outreach tasks.\n
- Ingestion points: LinkedIn engagement data retrieved via the
mcp__coldiq__extract_post_engagementtool.\n - Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the extracted data.\n
- Capability inventory: MCP tools are used to extract engagement data, find influencers, and identify signals.\n
- Sanitization: No explicit filtering or sanitization of the social media content is specified.\n- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to use
npx -y @coldiq/mcp@latest, which downloads and executes code from the npm registry. This is the standard deployment method for the vendor's integration tools.\n- [COMMAND_EXECUTION]: Provides specific shell commands for environment configuration and tool execution, including setting theCOLDIQ_API_KEYand launching the MCP server.
Audit Metadata