Wsdiscovery

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the local 'wsdiscovery' utility from the iothackbot suite to perform network scans and device enumeration.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists through the processing of untrusted metadata from network devices. 1. Ingestion points: Metadata fields such as manufacturer, model, and name are retrieved from external devices via the WS-Discovery protocol. 2. Boundary markers: No specific delimiters or safety instructions are used to isolate device-supplied data from the agent's core instructions. 3. Capability inventory: The skill has the capability to execute the wsdiscovery tool and parse its output. 4. Sanitization: No validation or filtering of external device strings is specified before the data is processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:00 AM