ClawHub
Back to skill

Security audit

Goody

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a read-only Goody connector, but its fallback setup instructions tell an agent to run remote installer scripts directly in a shell.

Review before installing. The Goody connector behavior itself is limited and read-oriented, but do not let an agent run the one-line remote installer automatically; install oo manually from a trusted source and verify the installer or package path first.

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 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 install endpoint, transport, or upstream distribution is compromised, arbitrary code could run on the host without review. The danger is elevated because the command appears in a troubleshooting/setup path inside an operational skill, making it plausible an agent would execute it automatically when oo is missing.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

For a markdown file, trigger language should be specific enough to avoid unintended invocation. Saying to use the skill for "ANY Goody request" is broad and does not provide exclusions, examples of non-matching cases, or scope limits beyond any task that "involves Goody."

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.