Skills
Navigate
skills/enuno/claude-command-and-control/tool-x-article-publisher/Gen Agent Trust Hub

tool-x-article-publisher

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown content from a user-provided file path which could be used to influence the agent's behavior during browser automation.
  • Ingestion points: scripts/parse_markdown.py reads and parses the Markdown file provided via article_md_path.
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted content from the agent's core instructions.
  • Capability inventory: The skill uses browser automation (Playwright), writes artifacts to /tmp/, and manipulates the system clipboard.
  • Sanitization: scripts/parse_markdown.py uses basic regex for HTML conversion, which does not sanitize for instructions that could influence the agent's subsequent browser interactions.
  • [COMMAND_EXECUTION]: The skill relies on executing local Python scripts bundled with the package to perform its tasks.
  • Execution of scripts/parse_markdown.py for data processing.
  • Execution of scripts/copy_to_clipboard.py which uses the AppKit and Foundation frameworks to interact with the macOS system clipboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 02:39 PM