nested-subagents
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized exfiltration attempts were detected within the skill's instructions or metadata.
- [PROMPT_INJECTION]: The skill establishes an ingestion point for user-supplied problem statements that are passed to sub-agents via the Task tool. This represents a standard surface for indirect prompt injection common in orchestrator agents.
- Ingestion points:
<problem-statement>argument in SKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined in the provided prompt template.
- Capability inventory: The skill has access to Task, TodoWrite, Read, Grep, Glob, and Bash as defined in the allowed-tools configuration.
- Sanitization: No explicit sanitization or input validation is described for the problem statement before it is delegated to sub-agents.
Audit Metadata