pricing
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a potential surface for indirect prompt injection.
- Ingestion points: Reads scraped text, reviews, and emails as defined in SKILL.md and references/skill-contract.md.
- Boundary markers: Includes explicit instructions to treat external data as untrusted and to ignore any embedded commands.
- Capability inventory: Can interact with CRM and payment platforms (Stripe, HubSpot) and perform file writes.
- Sanitization: Requires explicit user authorization for all side effects and persistent writes.
Audit Metadata