company-events

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to run a command that fetches a package from a public registry. Specifically, it mentions npx -y @coldiq/mcp@latest, which downloads the latest version of the ColdIQ MCP tool.
  • [COMMAND_EXECUTION]: The skill provides instructions for terminal command execution using npx to connect the MCP server. This is a standard setup procedure for the vendor's integration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources such as web searches, press releases, and LinkedIn announcements to identify company events. This represents an attack surface where malicious content embedded in news feeds could attempt to influence agent behavior.
  • Ingestion points: External websites (TechCrunch, PR Newswire, etc.), LinkedIn updates, and tool results from mcp__coldiq__search_web.
  • Boundary markers: None explicitly defined in the instructions to separate external data from system prompts.
  • Capability inventory: The skill uses tools to find signals and search the web, and reads local documentation files.
  • Sanitization: No specific sanitization or validation of the ingested external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 08:55 AM
Security Audit — agent-trust-hub — company-events