fetch-tweet
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches tweet data from the FxEmbed API service (api.fxtwitter.com). This is the primary mechanism for retrieving tweet information without requiring official API credentials.\n- [COMMAND_EXECUTION]: Uses a local Python script scripts/fetch_tweet.py to handle URL parsing and API interaction.\n- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting untrusted content from external X/Twitter posts.\n
- Ingestion points: Data is ingested via scripts/fetch_tweet.py from the external api.fxtwitter.com endpoint.\n
- Boundary markers: The instructions do not implement markers or specific guidance to the agent to isolate or ignore instructions that may be embedded in the fetched tweet text.\n
- Capability inventory: The script's capabilities are limited to performing network GET requests and outputting text to the console; no privileged operations or file system writes are performed.\n
- Sanitization: The script performs standard JSON parsing of the API response but does not sanitize the text content for potential prompt injection patterns before presentation to the agent.
Audit Metadata