ClawHub
Back to skill

Security audit

API Route

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly coherent API Route connector, but it under-describes billable model inference and includes unsafe one-line remote installer instructions.

Review before installing. Use this only if you intend to route API Route requests through OOMOL, and treat chat completion calls as billable external data transmission that should be explicitly approved with the prompt and model. Install the `oo` CLI through a verified method rather than blindly executing the piped installer commands.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (4)

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The skill instructs the agent to install software via curl ... | bash, which downloads and immediately executes a remote script without verification. If followed automatically or with limited review, this creates a supply-chain execution path where compromise of the host, TLS interception, or script changes could lead to arbitrary code execution.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest and description claim this skill is for 'searching and reading data,' but the documented create_chat_completion action performs paid inference and can send user prompts to a third-party model endpoint. This mismatch can cause agents or users to invoke the skill under false assumptions about capability and side effects, weakening consent and safety expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction to use this skill for 'ANY API Route request' is overly broad and can trigger the skill whenever API Route is mentioned, even when the user's intent does not require this connector. Overbroad routing increases the chance of unnecessary third-party data disclosure, unintended costs, or bypassing more appropriate tools and safeguards.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The safety section states that untagged actions are reads and safe to run directly, but create_chat_completion is untagged despite being an outbound inference operation that transmits user content and incurs cost. This unsafe classification may cause automatic execution without the higher scrutiny normally applied to non-read or billable actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.