churn-prevention
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external data which introduces a potential attack surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to read context from files like
.agents/product-marketing.md(or.claude/product-marketing.md) and to gather details from the user about their churn situation and billing setup. - Boundary markers: There are no instructions provided to use delimiters or to treat the content of these external files as non-executable data, increasing the risk that embedded instructions could be obeyed.
- Capability inventory: The skill references various powerful CLI tools (e.g.,
stripe,posthog,customer-io) for implementing the retention strategies. - Sanitization: No validation or sanitization routines are specified for the ingested content.
Audit Metadata