cursor-agent-supervisor
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates the use of the cursor-agent CLI for task delegation to sub-agents. It defines a workflow for offloading tasks with specific scopes.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for delegation that involves passing instructions to sub-agents.
- Ingestion points: Task descriptions passed to the cursor-agent CLI in SKILL.md.
- Boundary markers: The skill recommends using a structured Markdown template for instructions to prevent ambiguity.
- Capability inventory: Execution of cursor-agent CLI commands through the shell.
- Sanitization: The skill instructs the agent to perform manual verification of sub-agent outputs and run automated test suites to ensure correctness.
Audit Metadata