x-tracker

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from X (tweets and bookmarks) and Notion pages to generate AI-powered digests and rewrites, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads tweet data from local JSON archives (e.g., in scripts/analyze.ts) and fetches page content from the Notion API (in scripts/notion.ts).
  • Boundary markers: The instructions for the rewriting sub-agent in SKILL.md do not specify the use of boundary markers or instructions to disregard potential commands embedded within the processed content.
  • Capability inventory: The skill possesses the capability to perform network requests to X, Notion, and Discord APIs, and has write access to the local file system for archiving data and generating reports.
  • Sanitization: The implementation includes basic text cleaning (whitespace removal and truncation) but lacks semantic sanitization to identify or neutralize instructions hidden within the tweet text.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 06:11 AM