jwt-token-validator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill lacks defenses against malicious instructions embedded in the data it is designed to analyze.
  • Ingestion points: JWT tokens and authentication patterns provided by the user in response to triggers.
  • Boundary markers: Absent. There are no delimiters or instructions to treat token content as untrusted data.
  • Capability inventory: The skill allows Bash(npm:*), Write, Read, and Grep, providing a significant impact surface if an injection occurs.
  • Sanitization: Absent. No validation or escaping of the input content is defined before the agent processes the tokens.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM