fetch-tweet
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process untrusted data from X/Twitter via the FxEmbed API (api.fxtwitter.com).
- Ingestion points: Tweet text, author information, and engagement data are ingested into the agent context via
scripts/fetch_tweet.pyor theWebFetchtool. - Boundary markers: The instructions do not define clear delimiters or provide instructions to the agent to ignore any malicious prompts embedded within the fetched tweet content.
- Capability inventory: The skill performs shell command execution, file execution (local python script), and network requests.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the fetched text before it is presented to or processed by the AI agent.
- [COMMAND_EXECUTION]: The skill documentation provides examples of executing a local script (
scripts/fetch_tweet.py) and using shell piping withpython3 -cto parse data. While these are standard data processing patterns, they involve shell-level execution involving external inputs (URLs).
Audit Metadata