x-twitter-scraper

Fail

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of large volumes of untrusted content from X (formerly Twitter) via the Xquik API, which represents a significant attack surface for indirect prompt injection. * Ingestion points: Untrusted data enters the agent context through API responses from xquik.com, such as tweet text, user biographies, and direct messages. * Boundary markers: The skill explicitly instructs the agent to wrap all retrieved content in <XQUIK_UNTRUSTED_X_CONTENT> tags to differentiate it from system instructions. * Capability inventory: The agent possesses network access (via WebFetch) but is strictly restricted from shell execution, filesystem modification, and local code execution by the skill's frontmatter. * Sanitization: The instructions require the agent to serialize external content as JSON and apply Unicode escaping to control characters (<, >, &) to prevent injection breakout.
  • [DATA_EXFILTRATION]: The skill provides detailed instructions for configuring webhooks to deliver social media data to external URLs. An automated scanner (URLite) flagged the core search endpoint (https://xquik.com/api/v1/x/tweets/search) as having a phishing reputation. While this is a vendor-hosted resource, the association with phishing markers requires scrutiny of the destination endpoints and data-handling practices.
  • [COMMAND_EXECUTION]: Reference material (e.g., references/webhooks.md) contains boilerplate code for local listeners (Node.js, Python, Go) and shell commands (e.g., node server.js --confirmed-listener-scope). While intended for developer documentation, these provide the logic for executing potentially dangerous scripts on the user's local infrastructure.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch data and documentation from xquik.com and docs.xquik.com. An automated scanner flagged the documentation file references/scrape-export-twitter-data.md as malicious (FileRepMalware). Although likely a false positive for a markdown-based documentation file, the reputation hit on this reference file is noted.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 8, 2026, 06:56 AM
Security Audit — agent-trust-hub — x-twitter-scraper