wsdiscovery
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to run the wsdiscovery command, which is a specialized tool for scanning network protocols and enumerating device capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill processes device-generated metadata that could be controlled by an attacker on the local network, presenting an indirect injection risk.
- Ingestion points: Data ingested from network device responses (XML and JSON metadata) during discovery via the wsdiscovery tool.
- Boundary markers: The instructions lack specific markers or guidelines to distinguish device-supplied data from system instructions.
- Capability inventory: The skill uses the wsdiscovery utility and suggests subsequent use of onvifscan for further interaction.
- Sanitization: There are no mentioned mechanisms for sanitizing or validating the information received from discovered devices.
Audit Metadata