The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data which could contain malicious instructions injected by an attacker who influences system logs or order attributes.
Ingestion points: System logs retrieved via logs_get_recent and order search hits retrieved through the OCAPI order_search endpoint (referenced in references/order-evidence.md).
Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions embedded within the processed logs or order data.
Capability inventory: The skill uses CLI tools (b2c), reads log files, and executes external HTTP POST requests.
Sanitization: There are no specified sanitization or validation steps for external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references external documentation for authentication procedures.
Evidence: The file references/order-evidence.md points to https://salesforcecommercecloud.github.io/b2c-developer-tooling/guide/authentication.
Context: This URL belongs to a vendor-owned domain associated with the skill's author and is used for providing authentication guidance.
[COMMAND_EXECUTION]: The skill relies on local CLI utilities to manage sessions and extract environment data.
Evidence: Instructions include the use of b2c setup inspect for environment resolution and b2c auth token --json for obtaining authentication tokens to be used in external requests.

b2c-order-failure-triage