conductor-new-track
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and internal logic do not contain any detected malicious patterns, base64 obfuscation, or unauthorized network operations.
- [PROMPT_INJECTION]: The skill displays an indirect prompt injection attack surface because it processes untrusted user input and incorporates it into generated project files.
- Ingestion points: Interactive user prompts (e.g., Feature Summary, User Story) and local project files (conductor/product.md, conductor/tech-stack.md, conductor/workflow.md).
- Boundary markers: Absent. User input and file content are interpolated directly into markdown templates without delimiters or 'ignore' instructions.
- Capability inventory: The skill utilizes file system write capabilities to create and update track-related documentation (spec.md, plan.md, index.md) and metadata within the local workspace.
- Sanitization: The skill does not perform explicit sanitization or escaping of the ingested content before writing it to the file system.
Audit Metadata