frontend-expert

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze and refactor user-provided source code, creating a surface for indirect prompt injection where malicious instructions could be embedded in code comments or data structures.\n
  • Ingestion points: The skill ingests untrusted content by reading local project files and source code through the 'Read', 'Grep', and 'Glob' tools.\n
  • Boundary markers: There are no boundary markers or explicit safety instructions to help the agent distinguish between its system guidelines and instructions potentially embedded in the source code it processes.\n
  • Capability inventory: The skill possesses extensive capabilities, including 'Bash', 'Write', and 'Edit', which could be leveraged to perform unauthorized actions if the agent is manipulated by instructions found in user data.\n
  • Sanitization: No sanitization or validation logic is defined to filter or escape content retrieved from the file system before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 11:43 PM