leadgenius-cli
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill defines workflows for ingesting untrusted data from lead files and third-party scrapers, creating a surface for indirect prompt injection.\n
- Ingestion points: Lead data is ingested through the
leads importcommand (via--fileor--data) and lead generation runs (Apify) described inSKILL.mdandreferences/api_endpoints.md.\n - Boundary markers: Absent. The agent is not instructed to use delimiters or specific ignore-embedded-instructions rules for the ingested lead data.\n
- Capability inventory: The agent has capabilities to modify lead records (
leads update), trigger enrichment tasks (tasks enrich), and deliver leads to email platforms (email-platforms send).\n - Sanitization: Absent. There is no evidence of filtering or validation logic applied to ingested lead data fields like names or titles before they are processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill makes authenticated network requests to vendor APIs to facilitate lead management and scoring tasks.\n
- Requests target official domains
https://api.leadgenius.appandhttps://backend.epsimoai.iofor LeadGenius Pro and EpsimoAI services respectively.
Audit Metadata