The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to handle external data from Documenso webhooks, which introduces a surface for indirect prompt injection.
Ingestion points: Data enters the system through an Express.js webhook endpoint as defined in the TypeScript examples.
Boundary markers: The implementation lacks explicit delimiters or instructions to the agent to ignore potentially malicious instructions embedded within the webhook payload (e.g., in document titles).
Capability inventory: The skill is configured with broad capabilities, including Bash, Read, Write, and Edit tools.
Sanitization: While the code provides structural validation and secret verification, it does not sanitize specific payload fields before they are logged or potentially processed by the agent.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute curl and ngrok commands. These are standard tools for local development and testing of webhook endpoints and are used appropriately within the context of the skill's documentation.

documenso-webhooks-events