lighthouse-audit

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to execute local shell commands via npm run (e.g., npm run lighthouse, npm run lighthouse:json) to perform audits and generate diagnostic reports. This is intended functionality for performance monitoring.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes data from external web audits which could contain malicious or misleading instructions within metadata or report findings.\n
  • Ingestion points: Data is read from lighthouse-report.json and markdown files located in the lighthouse-reports/ directory during the analysis workflow.\n
  • Boundary markers: There are no specific delimiters or instructions provided to the agent to treat report content as untrusted data or to ignore embedded instructions.\n
  • Capability inventory: The skill has the capability to execute local npm scripts and read/write files to the local filesystem.\n
  • Sanitization: The instructions do not define any validation or sanitization steps for the data extracted from the Lighthouse reports before it is processed for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:33 AM