baoyu-danger-x-to-markdown

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE] (HIGH): The skill is designed to manage and store sensitive authentication data, including environment variables X_AUTH_TOKEN, X_CT0, and local session cookies captured via Chrome. Handling session tokens in combination with unverified scripts is a high-risk activity.
  • [COMMAND_EXECUTION] (HIGH): The skill invokes npx -y bun to execute TypeScript files located in a subdirectory (scripts/main.ts). This pattern allows for arbitrary code execution with the permissions of the user running the agent.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The use of npx -y can trigger the download and execution of packages from the npm registry if they are not already present, potentially introducing unpinned or malicious dependencies at runtime.
  • [REMOTE_CODE_EXECUTION] (HIGH): The reliance on an opaque, 'private reverse-engineered' X API represents a massive security risk. There is no guarantee regarding the integrity of the data processing or where the authenticated requests are actually being routed.
  • [DYNAMIC_EXECUTION] (MEDIUM): The 'Extension Support' feature implements dynamic loading of configuration and behavior overrides from EXTEND.md files located in project or user home directories, which can be used to modify skill logic without changing the core source code.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 11:08 AM