nd
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and configuration do not contain any malicious patterns. No signs of credential harvesting, unauthorized network access, or command execution were found. The skill follows best practices by restricting implicit invocation and setting clear guardrails for its logic.
- [PROMPT_INJECTION]: The skill processes user-supplied task descriptions and content from sibling skill files to determine routing. This creates a potential surface for indirect prompt injection, though the risk is negligible within this specific context.
- Ingestion points: User arguments and sibling nd-*.md files.
- Boundary markers: Absent.
- Capability inventory: Reading local skill files.
- Sanitization: Absent.
Audit Metadata