nx-cloud-cache-investigator
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands, including the Nx CLI (
nx show) and Node.js scripts from the associatednx-cloud-apiskill, to diagnose workspace health and retrieve task data.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data from API responses, CI logs, and cache artifacts, which creates a potential vector for indirect prompt injection if those sources are compromised.\n - Ingestion points: Processes Nx Cloud API responses, CI logs (via
references/log-and-report-assets.md), and cache artifacts (viareferences/artifact-integrity.md).\n - Boundary markers: The skill provides instructions to redact error signatures and use
jqto select only specific fields from API responses, reducing the surface area for injection.\n - Capability inventory: Performs command execution (
nx,node,jq) and file system writes for temporary data storage and inspection.\n - Sanitization: Explicitly instructs the agent to redact log content and filter JSON responses before analysis.
Audit Metadata