skills/zrong/skills/tencent-docs/Gen Agent Trust Hub

tencent-docs

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The sheet.operation_sheet tool (defined in sheet/api/operation-api.md) allows the agent to generate and execute JavaScript code on the Tencent Docs platform. This is a high-capability feature that executes AI-generated logic against remote spreadsheet APIs.
  • [COMMAND_EXECUTION]: The skill uses local shell scripts (setup.sh, import_file.sh) and a Node.js utility (generate_slide.js) to manage tokens, perform file uploads, and handle asynchronous PPT generation. These scripts interact with the system environment and the mcporter CLI tool.
  • [EXTERNAL_DOWNLOADS]: The setup.sh script performs a global installation of the mcporter Node.js package. The skill also facilitates authentication by fetching tokens from docs.qq.com and uploading files to cloud storage URLs.
  • [PROMPT_INJECTION]: The skill has multiple prompt injection surfaces. First, the js-script-rule.md file contains defensive instructions against behavior overrides. Second, the scrape_url workflow ingests untrusted external content from the web into the agent's context without explicit sanitization or boundary markers (Category 8), potentially allowing indirect injection from malicious websites.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:25 AM
Security Audit — agent-trust-hub — tencent-docs