lead-enrichment

Warn

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [CREDENTIALS_UNSAFE]: The script scripts/enrich_lead.py accesses sensitive local configuration files, specifically ~/.env and ~/Documents/_projects/n8n-automations/.env, to retrieve API tokens.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data from external web sources into its synthesis prompt without sanitization or boundary markers.
  • Ingestion points: scripts/enrich_lead.py fetches content from Google searches, LinkedIn profiles, and Perplexity research.
  • Boundary markers: Synthesis prompts do not utilize clear delimiters or instructions to ignore commands within the fetched data.
  • Capability inventory: The skill can perform network requests via aiohttp and update records in the Attio CRM.
  • Sanitization: No content filtering or validation is performed on data retrieved from external sources before it is passed to the LLM.
  • [COMMAND_EXECUTION]: The skill workflow involves executing local Python scripts to coordinate API calls and validate enrichment data.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from well-known services including Apify and OpenRouter, and sends data to the Attio CRM API.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 05:28 PM