dispatching-parallel-agents

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (HIGH): High-risk attack surface identified in the parallel agent dispatch workflow. * Ingestion points: SKILL.md and references/agent-prompt-example.md use error messages and test outputs as primary prompt components. * Boundary markers: No delimiters or isolation techniques are used to separate untrusted data from instructions in the example templates. * Capability inventory: Agents are tasked with 'Fixing bugs' and 'Adjusting test expectations' in src/agents/, granting file-write capabilities. * Sanitization: No input validation or sanitization of the error/test content is suggested.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 09:38 AM