pricing-experiments
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection as it instructions the agent to process external data from Stripe, which could theoretically contain malicious instructions embedded in metadata or description fields.
- Ingestion points: The skill ingests data via Stripe MCP tools (
GetMcpTools,CallMcpTool), specifically subscription and price objects. - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the retrieved Stripe data.
- Capability inventory: The skill possesses capabilities to read from and write to the Stripe API, including creating new prices and updating subscriptions (
subscriptions.update). - Sanitization: The skill does not define specific sanitization or validation logic for the data retrieved from the Stripe API.
Audit Metadata