ClawHub
Back to skill

Security audit

ReadMe

Security checks for vulnerabilities and agentic risk

Overview

The ReadMe operations have clear approval rules, but the required CLI can also install and update other agent skills without this skill explaining that behavior.

Review the CLI's broader installation effects before proceeding. Use a reviewed installation and disable unwanted startup skill synchronization using the publisher-documented OO_SKILLS_SYNC_DISABLED setting. See the [CLI environment controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Connect only the intended ReadMe account and approve exact edits or deletions. The remote installers and deployed connector service remain unverified.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command executes an Oomol-hosted installer rather than performing the declared ReadMe operations. Nothing in the supplied chunk establishes that this installation supports ReadMe functionality, so the unrelated remote-code execution is a material mismatch. The downloaded script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The installation instructions pipe remotely fetched content directly into Bash, and the Windows alternative similarly executes downloaded content without an independent integrity check. Compromise of the installer endpoint or distribution infrastructure could therefore execute arbitrary code with the invoking user's privileges, potentially exposing local files and credentials. Restricting installation to a missing-CLI error reduces exposure but does not establish the downloaded code's trustworthiness.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources