ideal-customer-profile-matching
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill describes an architecture for processing untrusted conversation data to influence agent behavior, which creates a surface for indirect prompt injection.
- Ingestion points: The
update_icp_during_conversationfunction inSKILL.mdprocesses untrusted prospect messages via themessageparameter. - Boundary markers: The logic snippets do not include delimiters or instructions for the agent to ignore commands that may be embedded in the prospect's input.
- Capability inventory: The skill uses extracted data to drive automated messaging in
customize_message_for_icpand perform automated lead routing inroute_by_icp. - Sanitization: There is no evidence of input validation or filtering before the conversation signals are used to update the system state.
- [EXTERNAL_DOWNLOADS]: The Python code snippets reference the well-known
scikit-learnlibrary for machine learning functionality.
Audit Metadata