Skills
skills/thierryteisseire/leadgenius-skill/leadgenius-api/Gen Agent Trust Hub

leadgenius-api

Fail

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • Category 2 (Data Exposure & Exfiltration) (HIGH): Hardcoded API credentials found in multiple script files. * Evidence: The scripts scripts/create_edu_demo.py, scripts/create_fin_demo.py, and scripts/fix_leads.py contain the hardcoded key da2-5u4a7hbhvbb2fdsj2ys2h2pljy passed as the x-api-key header to a production AWS AppSync GraphQL endpoint.
  • Category 8 (Indirect Prompt Injection) (LOW): The skill provides a surface for indirect prompt injection by processing external data from CSV files. * Ingestion points: scripts/import_csv.py (reads data from user-supplied CSV files). * Boundary markers: Absent. No specific delimiters or instructions are used to separate untrusted data from the agent's internal logic. * Capability inventory: The skill uses the requests library across scripts/api_call.py, scripts/auth.py, scripts/import_csv.py, and scripts/lead_distribution.py to perform network operations. * Sanitization: Absent. No escaping or validation is performed on the CSV fields before they are incorporated into API requests.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 20, 2026, 01:21 PM