spawn-research-agents

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: Analysis of the orchestration instructions confirms that the skill is intended for internal agent management and does not contain malicious patterns or safety bypasses.
  • [NO_CODE]: The skill consists exclusively of markdown documentation and metadata; no code files, packages, or binaries are present.
  • [PROMPT_INJECTION]: The skill establishes an orchestration workflow that processes user research questions as input for sub-agents, representing an indirect prompt injection surface.
  • Ingestion points: User-provided research questions are passed to sub-agents via the prompt parameter in the Task examples within SKILL.md.
  • Boundary markers: The instructions do not define explicit delimiters to separate user input from orchestration commands.
  • Capability inventory: The skill leverages sub-agents like codebase-locator and codebase-analyzer which typically have file-system read access.
  • Sanitization: No specific input sanitization or validation logic is prescribed for the user-defined research prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 10:32 PM