churn-prevention
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown documentation, strategy guides, and UI templates. No executable scripts, command-line operations, or network requests are present within the skill content.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface by instructing the agent to read an external context file.
- Ingestion points:
.agents/product-marketing-context.md(referenced in SKILL.md). - Boundary markers: None provided in the instructions for the file reading step.
- Capability inventory: The skill provides advisory instructions and recommends the use of standard CLI tools (Stripe, PostHog, etc.), but does not perform any file-write, network, or subprocess operations itself.
- Sanitization: No sanitization or validation logic is defined for the content of the marketing context file.
Audit Metadata