skills/wmy2981/skills/linkgo/Gen Agent Trust Hub

linkgo

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/linkgo.py executes the chcp 65001 command on Windows platforms to set the console output to UTF-8. This is a standard environment configuration step to ensure proper character encoding.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a management surface for remote service cards that support Markdown, HTML, and javascript: protocol links, which could be exploited if the agent processes malicious data.
  • Ingestion points: CLI arguments for the add, edit, page, and import commands in scripts/linkgo.py, which accept JSON strings containing card and page metadata.
  • Boundary markers: Absent; the skill is designed to directly apply configuration as requested by the user or agent.
  • Capability inventory: The skill can modify the remote application's state, including creating or deleting service cards, uploading files via upload-icon, and changing administrative credentials.
  • Sanitization: While the script validates the JSON structure, it does not sanitize the contents of the fields before transmitting them to the LinkGo API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:08 AM
Security Audit — agent-trust-hub — linkgo