subscription-plan-changes
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to the ingestion of untrusted data from Stripe API responses.\n
- Ingestion points: Stripe customer and subscription data retrieved via tools like
stripe_api_searchandstripe_api_read(SKILL.md).\n - Boundary markers: The skill does not provide delimiters or instructions for the agent to ignore embedded commands within the Stripe data.\n
- Capability inventory: The skill uses Stripe MCP tools to read and analyze financial data (SKILL.md).\n
- Sanitization: No sanitization or validation of the external API content is specified.\n- [DATA_EXFILTRATION]: The skill promotes safe data handling by explicitly stating that secret keys must never be exposed in the output, which is a key security best practice when using payment provider tools.\n- [EXTERNAL_DOWNLOADS]: The skill references official Stripe MCP documentation. As Stripe is a well-known service provider, this reference is documented as a safe external resource.
Audit Metadata