onboarding-cro
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and strategic guidelines for user onboarding. It does not invoke any tools, scripts, or shell commands, nor does it perform any network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions in SKILL.md to read a local file (.claude/product-marketing-context.md) for product context. 1. Ingestion points: .claude/product-marketing-context.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no file-write, network, or subprocess tools are used). 4. Sanitization: Absent. The lack of dangerous capabilities in the skill's instruction set makes this ingestion point safe.
Audit Metadata