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_TOOLSendpoint (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_TOOLandRUBE_REMOTE_WORKBENCHto 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