ClawHub
Back to skill

Security audit

Workpath

Security checks for vulnerabilities and agentic risk

Overview

The Workpath reads fit the stated purpose, but setup directs the agent to run unverified remote installation code without first asking you.

Review and install a verified CLI version separately, and require approval before the agent performs setup. Consider that OOMOL mediates access to your Workpath account and that the CLI may also install or update agent skills. The remote installation code is outside the reviewed package, so its complete effects remain unknown.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code performs remote installer execution rather than the declared Workpath data-access functionality. Nothing in the chunk establishes this installer as a supporting dependency for Workpath. The downloaded script is not supplied, so its subsequent actions cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes mutable network content directly into Bash without pinning or independently verifying the installer. Compromise of the hosting or release infrastructure could execute attacker-controlled code with the invoking user's privileges; HTTPS does not protect against a compromised publisher, although execution is conditional on the CLI being absent.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning about local code execution and system changes.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

A missing CLI triggers instructions to execute a remote installer without explaining local changes or obtaining explicit approval. This expands a Workpath read request into local software installation; the missing-command prerequisite limits exposure, and enforced tool permissions may block execution, but neither supplies informed user consent.

Content

No source excerpt is available for this finding.

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 83)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