ClawHub
Back to skill

Security audit

Holded

Security checks for vulnerabilities and agentic risk

Overview

The Holded actions require appropriate approval, but the required CLI can install or refresh skills across agent apps without this skill explaining those effects.

Review and preinstall a trusted CLI version before using this skill. Set OO_SKILLS_SYNC_DISABLED=1 for every oo invocation unless you want cross-agent skill management. OOMOL mediates access to your connected Holded account; approve each proposed write. The downloaded installers and deployed CLI version were not verified.

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
97% confidence
Finding

The supplied code performs remote installer execution rather than any visible Holded data operation. Although installation can be a supporting implementation detail, this chunk provides no evidence that the Oomol installer is required for Holded access. The remote script's contents are not supplied, so its subsequent behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command pipes a remotely fetched, mutable script directly into Bash without inspecting it or verifying a pinned artifact; the PowerShell alternative has the same execution pattern. If the distribution endpoint or its supply chain is compromised, attacker-controlled code could execute with the agent process's permissions and access local credentials or files. The missing-CLI condition limits exposure frequency but does not mitigate that execution risk.

Content

Scanner excerpt · SKILL.md (reported line 59)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 80)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