lead-qualification

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The script scripts/enrich_leads.py transmits user-provided LinkedIn profile URLs and API tokens to the vendor's proxy endpoint at app.gooseworks.ai. This is functional behavior for the lead enrichment process but involves sending data and credentials to external infrastructure.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted external data.
  • Ingestion points: LinkedIn profile data (headlines, bios, experience) fetched via Apify, as well as data from Google Sheets and CSV files.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands when passing lead data to subagents.
  • Capability inventory: The skill utilizes file system operations (saving prompts and results), network requests (Apify API, web search, and fetching profile pages), and Google Sheets management via the Rube MCP.
  • Sanitization: There is no evidence of filtering, escaping, or validation of the external content before it is interpolated into the context for qualification subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:05 PM
Security Audit — agent-trust-hub — lead-qualification