audit-website
Fail
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (CRITICAL): Confirmed detection of the pattern 'curl -fsSL https://squirrelscan.com/install | bash' in the skill installation or execution context. This allows an untrusted remote server to execute arbitrary shell commands on the host machine.
- [EXTERNAL_DOWNLOADS] (HIGH): The skill performs downloads from 'squirrelscan.com', which is not a recognized or trusted source according to security policy.
- [COMMAND_EXECUTION] (MEDIUM): The skill documentation promotes the execution of the 'squirrel' CLI tool, which performs system-level auditing and processes data from external URLs.
- [SAFE] (SAFE): The LLM format description includes best practices for output sanitization, such as XML character escaping, to mitigate potential indirect prompt injection or schema confusion when processed by an AI agent.
Recommendations
- HIGH: Downloads and executes remote code from: https://squirrelscan.com/install - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata