smartlead-workflows
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent processes external data, specifically lead lists (CSV uploads) and incoming email replies for AI categorization. This creates a surface for indirect prompt injection if the external data contains instructions for the agent.
- Ingestion points: Phase 2 (Lead list CSV upload) and Phase 3 (AI Reply Categorization of email replies) in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands when processing this external content.
- Capability inventory: The skill includes a local validation script (scripts/check-output.py) and references to vendor CLI tools (leadmagic-cli).
- Sanitization: There are no explicit instructions for sanitizing or filtering the content of lead lists or email replies before processing.
Audit Metadata