frontend-review-testing

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at scripts/audit-coverage.sh. It passes a repository path as a command-line argument to perform the coverage audit.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external sources (the repository being audited) which could theoretically contain malicious instructions embedded in configuration or report files.
  • Ingestion points: Reads files from the target repository including coverage/coverage-summary.json, package.json, vitest.config.*, and playwright.config.*.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers when interpolating file contents into the agent's context.
  • Capability inventory: The skill has the ability to execute shell scripts and write report files to the local filesystem.
  • Sanitization: No specific sanitization or validation logic is defined for the contents of the files read from the audited repository.
  • [FILESYSTEM_WRITE]: The skill generates a markdown report and writes it to a specific subdirectory (.frontend-review/report/latest/md/) within the target project's directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 03:37 AM
Security Audit — agent-trust-hub — frontend-review-testing