daytona-integration
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Remote Code Execution (HIGH): The skill contains the command 'curl -fsSL https://claude.ai/install.sh | bash'. This pattern is a known high-risk vector because it downloads and executes code from a remote server without any verification, integrity checks, or manual review by the user.
- External Downloads (MEDIUM): The script is downloaded from 'https://claude.ai'. While this domain is associated with Anthropic, it is not included in the 'Trusted External Sources' whitelist provided in the security skill instructions. Per the [TRUST-SCOPE-RULE], downloads from non-whitelisted sources for the purpose of execution are considered untrusted, especially when combined with immediate execution methods.
Recommendations
- HIGH: Downloads and executes remote code from: https://claude.ai/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata