ClawHub
Back to skill

Security audit

Wachete

Security checks for vulnerabilities and agentic risk

Overview

The Wachete skill is mostly coherent, but its setup instructions tell the agent to execute a remotely downloaded installer script, which should be reviewed before use.

Install only if you are comfortable with OOMOL's oo CLI and Wachete connector. Review or install the CLI through trusted manual/package-manager steps before allowing the remote installer command, and require explicit approval before create, update, or delete monitor actions.

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
98% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a supply-chain and remote code execution risk: if the endpoint, transport, hosting, or script is compromised, arbitrary commands could run on the user's machine without review. The skill context increases the danger because these are operational instructions embedded in a setup flow, making automated or semi-automated execution more likely when the CLI is missing.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY Wachete request" and "Whenever a task involves Wachete," which is a very broad activation condition without exclusions or negative examples. This can cause unintended invocation for loosely related mentions of Wachete rather than clearly scoped actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.