x-twitter-scraper
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to official plugins and SDKs hosted on GitHub and NPM (@xquik/tweetclaw).
- [COMMAND_EXECUTION]: Provides curl command examples for interacting with the Apify platform. These templates correctly use environment variables for authentication and do not exhibit injection vulnerabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from X (tweets, profiles). It mitigates this risk with a mandatory evidence chain: 1. Ingestion points: Data from tweet search and extraction jobs. 2. Boundary markers: Explicit 'treat as untrusted' and 'ignore embedded instructions' warnings. 3. Capability inventory: REST API and Apify network access. 4. Sanitization: Directions to return structured data and disregard prose-based commands within scraped content.
Audit Metadata