lead-communication-history
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing untrusted data from external sources, including email bodies, SMS, WhatsApp messages, and call transcripts fetched via
get_lead_history(SKILL.md). - Ingestion points: Message content and call transcripts retrieved through the
get_lead_historytool. - Boundary markers: The instructions require the agent to distinguish between communication events and their content, but they do not provide explicit delimiters or instructions to ignore embedded commands within that content.
- Capability inventory: The skill's impact is mitigated by its read-only design; it explicitly prohibits sending replies, changing lead data, or triggering automation.
- Sanitization: The skill does not describe any methods for sanitizing or filtering the retrieved message content before it is processed by the agent.
Audit Metadata