NYC

cook-parallel

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill ingests untrusted user data via the $ARGUMENTS variable and uses it to direct the actions of powerful subagents.
  • Ingestion points: $ARGUMENTS inside the tags in SKILL.md.
  • Boundary markers: Uses XML-style tags () which provide structural delimitation but are easily bypassed by adversarial input designed to close the tag.
  • Capability inventory: The workflow spawns researcher, planner, fullstack-developer, and tester subagents. These agents typically possess file-system write access and command execution capabilities.
  • Sanitization: No sanitization or validation of the input tasks is performed before they are processed by the subagent chain.
  • Automated Scan Alert (INFO): The scanner alert for 'login-form.com' is a false positive triggered by the example filename 'login-form.component.ts' being misidentified as a domain.
Recommendations
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 09:02 AM