x-tweet-ego

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (X.com) during the validation and quoting workflows.
  • Ingestion points: The script reads tweet content from article elements and status updates from toast notifications ([data-testid="toast"]) into the agent's context.
  • Boundary markers: No specific delimiters or instructions are used to separate the external content from the agent's internal logic.
  • Capability inventory: The agent has the ability to navigate, type, and click within a browser environment via the ego-browser tool.
  • Sanitization: While the skill does not sanitize the text it reads, it correctly uses JSON.stringify() when interpolating user-provided text into the automation scripts, preventing command injection attacks during the execution phase.- [COMMAND_EXECUTION]: The skill executes complex browser automation logic via ego-browser nodejs. These scripts are executed locally and are restricted to the browser automation environment. The skill follows best practices by using "gates" (checks for DOM state and text matching) before performing final actions like clicking the 'Post' button.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 08:52 PM
Security Audit — agent-trust-hub — x-tweet-ego