The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to fetch data from external REST API endpoints, which introduces a potential surface for indirect prompt injection if the external data source is untrusted. \n- Ingestion points: Data retrieved from /api/billing/plans, /api/billing/subscription, and Stripe-provided URLs. \n- Boundary markers: None; the skill does not specify delimiters or instructions to ignore commands within the data. \n- Capability inventory: No scripts or tool definitions are included within the skill itself; capabilities are limited to documentation-based API calls. \n- Sanitization: The skill lacks instructions for validating or sanitizing external API responses. \n- [NO_CODE]: The skill consists entirely of Markdown documentation and does not include any scripts, tools, or binary files.

billing-management