churn-prevention
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external context from files such as
.agents/product-marketing.mdto inform its strategy recommendations, creating a potential surface for indirect prompt injection. - Ingestion points: The skill attempts to read
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md(SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when reading these context files.
- Capability inventory: The skill references the use of CLI tools including
stripe,customer-io,posthog,mixpanel,ga4, andsegmentfor implementing retention strategies (SKILL.md). - Sanitization: The skill does not describe any sanitization or validation process for the data read from the marketing context files.
Audit Metadata