perf-audit

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to audit performance, including project-specific build scripts and standard analysis tools via npx.
  • Evidence includes usage of gzip, wc, and npx to run utilities like source-map-explorer and webpack-bundle-analyzer.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and acts upon content from a project's package.json file.
  • Ingestion points: Reads package.json to detect build tools and scripts.
  • Boundary markers: None specified in the skill instructions to separate untrusted project data from agent instructions.
  • Capability inventory: The skill has the capability to execute shell commands (npx, gzip) and run production build tasks defined within the project files.
  • Sanitization: No explicit sanitization or validation of the build scripts found in package.json is described before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:14 PM
Security Audit — agent-trust-hub — perf-audit