frontend-perf

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to analyze and modify external frontend source code while having access to the 'Bash' tool. This creates a risk where malicious instructions hidden in the analyzed code could influence the agent's actions.
  • Ingestion points: The agent uses Read, Glob, and Grep tools to ingest external source code files.
  • Boundary markers: Absent. There are no instructions defining boundaries between system prompts and user-provided code.
  • Capability inventory: The agent has 'Bash', 'Write', and 'Edit' capabilities, allowing for significant system impact if misdirected.
  • Sanitization: No sanitization or validation logic is defined for the content of processed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 06:18 AM