ClawHub
Back to skill

Security audit

Oauth Oidc

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only OAuth/OIDC guidance skill with no executable behavior or hidden data access.

Install this as an OAuth/OIDC reference workflow. It is not executable and does not access credentials, but users should still treat generated auth guidance as design advice and verify provider-specific details against their identity provider documentation.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
## Stage 3: Tokens & Validation

**Goal:** **Access token** for APIs; **ID token** for identity claims—validate **issuer**, **audience**, **exp**, **signature** (JWKS rotation).

### Practices

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The 'Trigger conditions' section lists general situations like web/mobile login, machine-to-machine clients, and debugging token or redirect issues, but it does not define specific invocation phrases, scope limits, or negative examples. This could cause the skill to be offered in many common authentication-related conversations without clear boundaries for when it should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.