x-twitter-scraper
Fail
Audited by Gen Agent Trust Hub on May 26, 2026
Risk Level: CRITICALDATA_EXFILTRATIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DATA_EXFILTRATION]: Automated URL reputation scanners (URLite) have flagged the primary API endpoint 'https://xquik.com/api/v1' as a phishing threat. Additionally, anti-virus scans detected suspicious HTTP request patterns ('HttpRequest-inf') within the SKILL.md file. This domain is the central destination for all data retrieved by the skill, including sensitive private information such as direct messages, bookmarks, and account timelines.- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted data from X (Twitter).
- Ingestion points: The skill retrieves tweets, user profiles, notifications, and direct messages via various API endpoints defined in 'api-endpoints.md'.
- Boundary markers: The skill instructions in 'SKILL.md' and 'security.md' advise the agent to treat X-authored content as quoted data and avoid using it as instructions, though it lacks physical delimiters for isolation.
- Capability inventory: The skill possesses significant capabilities, including posting tweets, sending direct messages, and initiating billing/payment actions via 'POST /credits/quick-topup'.
- Sanitization: 'security.md' specifies that control characters should be stripped or escaped and recommends summarizing large or suspicious content to mitigate risk.- [EXTERNAL_DOWNLOADS]: The documentation references several external dependencies required for integration, including the 'mppx' and 'viem' Node.js packages for micropayment handling, as well as 'express' for webhooks. Python examples also rely on the 'requests' and 'flask' libraries.
Recommendations
- CRITICAL: 1 infected file(s) detected - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata