nmt-product-requirements

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands to read a local version file and perform a network request using curl for update checks.
  • [DATA_EXFILTRATION]: The update mechanism transmits the contents of a local file (.nmt-version) to the domain nextmovetheory.com. While the data is limited to version information, this establishes a network exfiltration pattern to a non-whitelisted domain.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection through the ingestion of untrusted external data.
  • Ingestion points: The skill ingests user-supplied materials such as Notion exports, research notes, and interview transcripts during the S0 intake phase.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between instructions and untrusted data.
  • Capability inventory: The skill possesses the ability to spawn subagents via the Agent tool, perform web searches in Deep mode, and write to the local filesystem.
  • Sanitization: The skill does not define any sanitization or validation mechanisms for the ingested user content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 09:31 AM
Security Audit — agent-trust-hub — nmt-product-requirements