ClawHub
Back to skill

Security audit

Jibble

Security checks for vulnerabilities and agentic risk

Overview

The Jibble skill is mostly purpose-aligned, but it needs review because its setup instructions can execute remote installer scripts and the connector can perform destructive Jibble changes.

Install only if you trust OOMOL and the oo CLI installer source. Prefer a verified or package-manager install path, and make sure the agent asks before installing software or running any write/destructive Jibble action. Confirm the exact organization, location, payload, and effect before allowing updates or deletions.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

md
- `create_location` — Create a work location in Jibble. [write]
- `delete_location` — Permanently delete a Jibble work location. [destructive]
- `get_organizations` — List the Jibble organizations accessible to the personal access token.
- `list_locations` — List Jibble work locations with optional OData filtering and pagination.
- `list_members` — List people in the Jibble organization with optional OData filtering and pagination.
- `update_location` — Update or archive an existing Jibble work location. [destructive]

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill includes a one-line remote script execution pattern (curl ... | bash) for installing the CLI. This is dangerous because it executes code fetched at runtime from an external server without integrity verification, and since the skill content is operational guidance to an agent, it could lead to unreviewed code execution on the host when setup errors occur.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger scope is excessively broad: it directs the agent to use this skill for any Jibble-related task, including read, write, and destructive actions. Broad routing increases the chance the skill is invoked in inappropriate contexts and can funnel users into state-changing connector operations without sufficient task-level scoping or exclusions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.