customerio-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the processing of external data.
- Ingestion points: Data is ingested from the Customer.io API in
references/implementation.mdandscripts/cio-cleanup-inactive.ts(via the target list). - Boundary markers: The instructions do not specify the use of delimiters or boundary markers for the external data ingested.
- Capability inventory: The skill includes scripts that perform network requests and account modifications (suppress/destroy profiles) across all files (
SKILL.md,references/implementation-guide.md,references/implementation.md). - Sanitization: The skill lacks explicit sanitization or validation of the data fields retrieved from the API before they are used in control logic.
Audit Metadata