The Agent Skills Directory

[SAFE]: The skill uses environment variables (X_BEARER_TOKEN, X_API_KEY, etc.) for managing API credentials, which is a standard security best practice. The documentation explicitly advises against hardcoding tokens or committing secrets to version control.
[PROMPT_INJECTION]: The skill fetches external data from the X platform, creating an attack surface for indirect prompt injection if the agent processes the retrieved text as instructions. Ingestion points: SKILL.md snippets for searching tweets and reading user timelines via the api.x.com endpoints. Boundary markers: None provided in the code examples to distinguish between API data and system instructions. Capability inventory: Performs network requests (requests.get, oauth.post) and file reading (open("image.png", "rb")) for media uploads. No dynamic code execution or system modification capabilities are used. Sanitization: The examples demonstrate direct retrieval of JSON data without explicit sanitization or filtering of the content fields.

x-api