churn-prevention
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from user-supplied cancellation reasons and survey responses.
- Ingestion points: User input gathered for the exit survey and product context as described in SKILL.md and references/cancel-flow-patterns.md.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions within user-supplied input.
- Capability inventory: The skill references and encourages use of external CLI tools such as stripe, customer-io, and posthog.
- Sanitization: No specific sanitization or filtering logic is prescribed for user-supplied strings.
Audit Metadata