omniroute-web-fetch
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core purpose is to fetch arbitrary content from external URLs and provide it to the agent. This content is untrusted and may contain malicious instructions designed to manipulate the LLM's behavior.
- Ingestion points: The
urlparameter allows fetching content from any web server. - Boundary markers: No specific delimiters or safety instructions are defined to separate the fetched content from the agent's instructions.
- Capability inventory: The skill uses
curlto perform network requests. - Sanitization: No sanitization or filtering of the fetched content is specified before it is returned to the agent.
- [COMMAND_EXECUTION]: The skill provides example
curlcommands for discovery and execution. While these are intended for API interaction, they demonstrate a reliance on shell commands that handle environment variables ($OMNIROUTE_URL,$OMNIROUTE_KEY).
Audit Metadata