workspace-performance-audit

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides the agent with a series of shell commands (e.g., ls, cat, grep, npx) and database queries (e.g., db.collection.stats()) to perform workspace discovery and collect performance metrics.
  • [INDIRECT_PROMPT_INJECTION]: A vulnerability surface exists because the skill ingests untrusted data from the monorepo, including package.json files, source code, and outputs from external diagnostic tools.
  • Ingestion points: Workspace configuration files (package.json), application source code, and results from Lighthouse and MongoDB profiler tools.
  • Boundary markers: Not explicitly defined in the provided orchestration guide for separating tool outputs from agent instructions.
  • Capability inventory: Shell execution (ls, cat, npx), database command execution, and file system write operations to the .agents/memory/ directory.
  • Sanitization: No explicit sanitization or validation of external content is described in the audit guide.
  • [EXTERNAL_DOWNLOADS]: The skill leverages the npx command to download and execute performance analysis tools such as @next/bundle-analyzer, lighthouse, and depcheck from the NPM registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:10 AM
Security Audit — agent-trust-hub — workspace-performance-audit