job-changes

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and execute the @coldiq/mcp package from the NPM registry using npx. This is a vendor-owned resource required to enable the skill's core search and tracking functionality.
  • [COMMAND_EXECUTION]: Includes a shell command (npx -y @coldiq/mcp@latest) to initialize the Cold-IQ MCP server, which is necessary for the agent to access specialized B2B intelligence tools.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process untrusted data from external LinkedIn profiles.
  • Ingestion points: LinkedIn URLs provided in the user's workspace or manual inputs (SKILL.md).
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill utilizes network-enabled MCP tools (mcp__coldiq__search_jobs, mcp__coldiq__find_signals) to query external databases (SKILL.md).
  • Sanitization: No specific validation or sanitization logic is described for the content retrieved from LinkedIn URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — job-changes