onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources like scraped text and reviews which could contain hidden instructions. * Ingestion points: Scraped page text, reviews, comments, and third-party exports (SKILL.md, references/skill-contract.md). * Boundary markers: Instructions explicitly state to treat such input as untrusted and not to follow embedded instructions. * Capability inventory: Potential access to marketing tools and RevOps platforms such as Google Ads, HubSpot, and Stripe (references/connectors.md). * Sanitization: The skill relies on conceptual instructions to the agent rather than technical sanitization logic.
- [NO_CODE]: The skill files consist entirely of markdown instructions and reference documentation without any executable scripts or binary files.
Audit Metadata