linkly-ai

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill README provides instructions to download and execute installation scripts for the 'linkly' CLI directly from the vendor's official update server (updater.linkly.ai). This includes shell scripts for Unix-like systems and PowerShell scripts for Windows environments.- [COMMAND_EXECUTION]: The agent is instructed to use the local terminal to execute linkly commands for searching documents, retrieving structural outlines, and running system diagnostics via the linkly doctor utility.- [PROMPT_INJECTION]: As the skill's primary function is to ingest and display content from external documents (PDF, Markdown, etc.), it presents an indirect prompt injection surface. To address this, the skill includes explicit safety guidelines directing the agent to treat all document content as untrusted data and to ignore any embedded instructions or commands found within them.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:34 AM
Security Audit — agent-trust-hub — linkly-ai