The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The script scripts/stripe_customers.py accesses the sensitive configuration file at ~/.config/stripe/config.json to retrieve the api_key. While this is standard for Stripe's own CLI tools, reading credential files is a security concern in the context of AI agent skills.\n- [COMMAND_EXECUTION]: The get command in scripts/stripe_customers.py performs unsafe string concatenation of the customer_id argument into the API URL (f\"/customers/{customer_id}\"). This lacks proper URL encoding or sanitization, potentially allowing path traversal against the Stripe API endpoint if a malicious ID is supplied.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data from the Stripe API.\n
Ingestion points: Customer profiles (names, emails, metadata) and subscription details are fetched from the external Stripe API in scripts/stripe_customers.py.\n
Boundary markers: External data is presented to the agent without any delimiters or instructions to ignore embedded commands.\n
Capability inventory: The skill possesses the ability to read local configuration files and perform network operations to the Stripe API.\n
Sanitization: No validation or sanitization of data retrieved from the API is performed before it is output to the agent context.

stripe-customers