The Agent Skills Directory

[SAFE]: The skill consists of documentation and instructional frameworks for SaaS retention. No malicious scripts, suspicious command executions, or persistence mechanisms were detected.
[SAFE]: The skill references well-known and reputable third-party services such as Stripe, PostHog, and Customer.io. These references are purely informational and consistent with the skill's purpose of subscription management.
[PROMPT_INJECTION]: The skill defines a surface for processing untrusted data by instructing the agent to read external context files like .agents/product-marketing.md if they exist.
Ingestion points: Files such as .agents/product-marketing.md or .claude/product-marketing.md (SKILL.md).
Boundary markers: None explicitly defined to separate untrusted context from internal instructions.
Capability inventory: The skill provides strategy advice and references external CLI tools (e.g., stripe, posthog) for potential use but does not contain automated scripts for executing them.
Sanitization: No validation or sanitization of the context file contents is performed by the skill.

churn-prevention