The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing external data from Retell AI webhooks and API responses. While this represents an attack surface for indirect prompt injection if the incoming data contains malicious instructions, the skill limits its operations to calculating metrics and generating reports.
Ingestion points: The webhook handler (references/monitoring-configs.md) and the API query script process external JSON data.
Boundary markers: No specific delimiters are used in the provided code examples to separate untrusted data from processing logic.
Capability inventory: The skill uses Bash(curl) and standard JavaScript processing.
Sanitization: The examples use structured property access and jq for parsing, which provides basic structural validation.
[COMMAND_EXECUTION]: The skill includes a bash script that uses curl to interact with the official Retell AI API (api.retellai.com). This is standard functionality for the service and correctly uses the $RETELL_API_KEY environment variable for authentication.

retellai-observability