test

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Potential indirect prompt injection surface via test tags.
  • Ingestion points: User-provided feature tags (e.g., @core) are used for filtering test execution in SKILL.md.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the skill definition.
  • Capability inventory: The skill triggers end-to-end testing via Playwright, which typically involves system command execution.
  • Sanitization: No validation, escaping, or sanitization logic for the user-supplied tags is specified.
  • [COMMAND_EXECUTION]: The skill's intended functionality involves executing shell commands (Playwright) using external input, which represents a potential command injection path if tags are maliciously crafted.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 02:23 PM
Security Audit — agent-trust-hub — test