nx-cloud-api

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the npx nx-cloud api command to interact with official Nx Cloud services. This is an expected and documented behavior for a skill developed by the vendor to interface with its own infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes JSON data and binary assets (logs, artifacts) retrieved from the external Nx Cloud API. If these sources were compromised, they could potentially serve malicious instructions to the agent.
  • Ingestion points: API response JSON, log files, and artifact downloads (SKILL.md, references/extraction-and-calculation.md).
  • Boundary markers: No explicit delimiters are suggested for separating ingested API data from instructions, although JSON projections are used.
  • Capability inventory: The agent can perform file writes, execute CLI commands via npx, and run custom scripts for calculations.
  • Sanitization: The skill instructs the agent to use jq projections to select only necessary fields, which acts as a basic form of data sanitization.
  • [DYNAMIC_EXECUTION]: The skill guides the agent to generate and execute custom scripts for processing and performing calculations on data retrieved from the API.
  • Evidence: The 'Calculation' section in references/extraction-and-calculation.md describes the requirement to write scripts that read saved JSON data and output results.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:29 PM