email-search
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes contact data from Extruct tables and local CSV files, representing an ingestion surface for untrusted data.\n
- Ingestion points: Data is loaded from
claude-code-gtm/csv/input/{campaign}/people_linkedin.csvor Extruct people tables.\n - Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.\n
- Capability inventory: The skill performs file reads/writes and makes network requests to external enrichment providers.\n
- Sanitization: No explicit sanitization of input data is described.\n- [COMMAND_EXECUTION]: The skill performs legitimate network operations by calling the APIs of well-known enrichment services (Prospeo and Fullenrich).\n- [DATA_EXFILTRATION]: The skill requests and uses API keys from the user to authenticate with third-party providers. This is a functional requirement for the lead enrichment process.
Audit Metadata