The Agent Skills Directory

[SAFE]: The skill provides documentation for interacting with the Deepgram Read API. All instructions and URLs are consistent with the vendor's primary purpose of providing text intelligence services.\n- [EXTERNAL_DOWNLOADS]: The skill references official Deepgram domains for API requests (api.deepgram.com) and technical documentation (developers.deepgram.com). These are legitimate vendor resources used for the skill's intended functionality.\n- [CREDENTIALS_SAFE]: The provided code snippets demonstrate the correct use of an environment variable ($DEEPGRAM_API_KEY) for authentication rather than providing hardcoded secrets.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted text data (e.g., support tickets, chat logs, or documents) via the text or url parameters.\n
Ingestion points: Data enters the context through the JSON payload (text field) or remote document fetching (url field) described in SKILL.md.\n
Boundary markers: None specified for the text input.\n
Capability inventory: The skill executes a REST POST request to an external API (api.deepgram.com) using curl.\n
Sanitization: No explicit sanitization of input text is mentioned.

text-intelligence