javascript-pro

Warn

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a 'skill-report.json' file with deceptive metadata claiming a security audit was performed by a non-existent AI model version ('gpt-5.5:high'). This represents an attempt to mislead safety evaluations through fabricated provenance documentation.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to analyze and process untrusted user-provided JavaScript code.
  • Ingestion points: User-supplied JavaScript source files and code snippets for debugging and refactoring (identified in SKILL.md).
  • Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore instructions embedded within the processed code.
  • Capability inventory: The agent generates functional code, Jest tests, and performance profiles based on the provided input.
  • Sanitization: No mechanisms are specified for the agent to validate or filter instructions within the code it processes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 6, 2026, 05:25 AM
Security Audit — agent-trust-hub — javascript-pro