Security audit

JWT Debugger

Security checks for vulnerabilities and agentic risk

Overview

This is a local JWT debugging skill, but some validation commands can execute injected Python if a token or key value is maliciously crafted.

Review before installing. The skill avoids external JWT websites and has no persistence, but its validation examples should be rewritten to pass tokens, secrets, keys, and audiences through stdin, files, or environment variables read by Python, not embedded into python3 -c source. Do not run the current validation snippets on tokens or key material supplied by an untrusted party.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:84
Finding: Arbitrary Python Code Execution Through Unsafe JWT Parameter Interpolation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation guidance includes broad phrases like "decode this token", "why is auth failing", and especially the fallback condition "when troubleshooting authentication," which can overlap with many general authentication support requests. The description does not provide exclusion conditions or boundaries for when this JWT-specific skill should not activate, increasing the chance of unintended invocation.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest and introductory documentation describe a troubleshooting tool for inspecting and validating existing tokens in authentication flows. The generate command expands the skill into token creation, which is a distinct capability not reflected in the stated description of decoding, validation, debugging, or diagnosis.
Content: No source excerpt is available for this finding.