ClawHub
Back to skill

Security audit

Waffo Pancake

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Waffo Pancake connector, but it needs review because it can affect payment/business data and includes unverified remote-script CLI installation steps.

Review the oo CLI installation path before installing. Prefer a verified or documented installer with version and integrity checks, and only allow Waffo write or destructive actions after checking the exact payload, target account, and expected business effect.

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
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill recommends installing the CLI via a network-fetched shell pipeline (curl ... | bash), which executes remote code immediately without verification. If the remote server, transport path, or install script is compromised, this can lead to arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description says to use this skill for ANY Waffo Pancake request, which is an overly broad routing trigger that can cause the agent to invoke a highly capable integration by default for almost all Waffo-related tasks. Because the skill includes both read and state-changing/destructive actions, over-invocation increases the chance of unintended data access or accidental execution of sensitive operations in the wrong context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.