ClawHub
Back to skill

Security audit

REST API

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only REST API helper with disclosed local project memory and no hidden execution, network calls, or credential access.

Before installing, decide whether you want the skill to keep local REST API project memory in ~/rest-api/. Avoid putting secrets, tokens, or personal data into that memory, and decline default logging if you only want one-off API guidance.

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
Content
## AuthN and AuthZ Separation

- Authenticate first (API key, session token, JWT, OAuth access token).
- Authorize second at resource boundary.
- Never trust client-provided roles without server verification.
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The setup asks broad activation questions such as whether the support should activate whenever the user asks to design or implement REST endpoints, and whether it should proactively enforce checks when API work appears risky. This creates unclear trigger boundaries, increasing the chance the skill will engage in contexts the user did not explicitly intend, which can lead to overreach, unwanted persistence, or inappropriate application of the skill's behaviors.

Static analysis

No suspicious patterns detected.