x-twitter-scraper

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing external social media content.\n
  • Ingestion points: The skill ingests untrusted data from X (Twitter) through multiple tools, including search-tweets, lookup-tweet, and various extraction tools (e.g., reply_extractor, post_extractor) defined in SKILL.md.\n
  • Boundary markers: There are no explicit instructions or delimiters provided in the skill configuration to help the agent distinguish between its instructions and the content of the tweets it retrieves.\n
  • Capability inventory: The skill provides 22 MCP tools that allow the agent to perform extensive data lookups, start/stop account monitoring, and manage webhooks via the https://xquik.com API.\n
  • Sanitization: The documentation does not specify any sanitization, filtering, or escaping of the retrieved tweet content before it is passed to the AI agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 06:53 PM