kai-sdr-reply-triage
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process inbound SDR replies from external, untrusted sources, creating a surface for indirect prompt injection attacks.
- Ingestion points: Inbound customer and prospect replies processed during the triage workflow (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the inbound text.
- Capability inventory: The skill performs file system writes to the workspace directory and triggers secondary automated skills such as /kai-sales-meeting-prep (SKILL.md).
- Sanitization: There are no specified mechanisms for sanitizing, escaping, or validating the content of the inbound messages before they are processed by the agent.
Audit Metadata