design-product-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration YAML. No executable scripts, binaries, or automated commands are included, which significantly limits the attack surface.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions suggest that the agent should ingest external data such as onboarding calls, customer signals, surveys, and support evidence. This represents a potential surface for indirect prompt injection if the processed data contains adversarial instructions.
- Ingestion points: Onboarding calls, signals, surveys, support evidence, account context, and documents.
- Boundary markers: None present in the instructions.
- Capability inventory: Searching organization skills and project documents via the BuildBetter MCP.
- Sanitization: No explicit sanitization or filtering of external content is defined.
Audit Metadata