churn-prevention
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather context from local project files such as
.agents/product-marketing.md. This represents a potential surface for indirect prompt injection if those files contain untrusted content. - Ingestion points: Reads
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.mdfor business context. - Boundary markers: None specified for the ingested content.
- Capability inventory: The skill mentions interaction with CLI tools for Stripe, Customer.io, and PostHog to manage subscriptions and analytics.
- Sanitization: No explicit sanitization of the input file content is performed.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known third-party services (Stripe, PostHog, Customer.io, Mixpanel, Segment) for implementation. These are standard industry tools for subscription management and analytics, and their mention is informative for the user's workflow.
Audit Metadata