ClawHub
Back to skill

Security audit

ConfigCat

Security checks for vulnerabilities and agentic risk

Overview

The ConfigCat read functions fit their purpose, but setup directs the agent to execute unverified downloaded software without a separate approval step.

Review the setup before enabling this skill. Preinstall a vetted CLI version and require approval before downloaded code executes. Check the CLI's automatic skill synchronization settings and connect ConfigCat with only the access needed. ConfigCat data passes through OOMOL as disclosed; the remote installers' exact behavior remains unverified. No malicious behavior was established.

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
99% confidence
Finding

The supplied command performs remote software installation rather than searching or reading ConfigCat data. Although installation can be a supporting implementation detail, this chunk establishes no relationship between the Oomol installer and the declared ConfigCat functionality. The downloaded script's contents and any additional effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live HTTPS response directly into Bash executes remote code without verifying a pinned version, signature, or independently trusted digest. Compromise of the distribution endpoint could yield arbitrary code execution with the agent's local privileges; the missing-CLI condition reduces exposure but does not protect execution.

Content

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

The fallback setup executes downloaded installation scripts without warning about remote-code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs installation when the CLI is absent without first obtaining approval for executing downloaded code and changing the local system. A request to read ConfigCat data does not itself authorize software installation, although the conditional setup limits when this risk arises.

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 82)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