onboarding-plan
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted external data including CRM exports, PDF documents, and meeting transcripts as specified in SKILL.md (Workflow Step 1) and references/input-rules.md (Rules 1, 3, 5).
- Ingestion points: Workflow Step 1 in SKILL.md accepts sales handoff notes and CRM data. references/input-rules.md specifies handling of PDFs, Slack pastes, and meeting transcripts.
- Boundary markers: SKILL.md (Section 0) contains explicit instructions for the agent to treat fetched or uploaded content as data only and never as instructions, providing a strong defensive boundary.
- Capability inventory: The skill instructions do not utilize high-risk tools such as shell execution, file writing, or arbitrary network requests.
- Sanitization: The skill relies on natural language instructions to disregard embedded commands in untrusted input.
Audit Metadata