scanner
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Network Operations]: The skill retrieves data from external URLs to generate the support corpus. This functionality is intended, but it involves network requests which are a consideration for potential Server-Side Request Forgery (SSRF) if non-public endpoints are targeted.
- [Untrusted Content Handling]: The skill parses HTML from third-party websites. This represents a surface for indirect prompt injection, as the resulting markdown files may contain text that could influence agent behavior when the corpus is later referenced during tasks.
- [File System Access]: The script saves generated files to the agent's workspace. This is a standard operation for this type of tool, and the script includes filename sanitization to prevent path traversal considerations.
- [Command Execution]: The skill utilizes a shell command to run a Python script with user-provided arguments. This is a common pattern for skill implementation, and the script uses standard argument parsing to manage inputs.
Audit Metadata