qualaroo-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it directs the agent to ingest and act upon tool discovery data from a remote endpoint. \n
  • Ingestion points: Tool schemas and execution plans returned by the RUBE_SEARCH_TOOLS endpoint (SKILL.md).\n
  • Boundary markers: Absent; the instructions advise the agent to follow the returned search results directly for tool execution.\n
  • Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform operations in the Qualaroo environment (SKILL.md).\n
  • Sanitization: No validation or sanitization of the remote tool descriptions or schemas is implemented in the skill instructions.\n- [NO_CODE]: The skill consists entirely of markdown documentation and does not provide associated executable scripts, source code, or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:39 AM