Security audit

Klangio

Security checks for vulnerabilities and agentic risk

Overview

The Klangio connector skill is mostly coherent, but its first-time setup recommends running unverified remote installer scripts directly in a shell.

Review this skill carefully before installing. Its Klangio operations are disclosed and user confirmation is required for writes, but do not run the provided curl | bash or irm | iex installer commands blindly. Install the oo CLI through a safer official or verified method, and confirm exact payloads before creating Klangio processing jobs or uploading result files through OOMOL transit storage.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:63
Finding: Unverified Remote Installer Download and Immediate Execution
Content: View full analysis
Remediation: View remediation
/install.sh" echo " install.sh" | sha256sum --check - less install.sh bash install.sh ``` The version and digest must be real, publisher-provided values obtained through a trusted channel; placeholders must never be used operationally. ]]>

SkillSpector

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

External Script Fetching

High

Category: Supply Chain
Confidence: 97% confidence
Finding: The skill instructs the agent to install software by piping a remotely fetched script directly into a shell, which creates a classic remote code execution risk if the host, CDN, connection, or script contents are compromised. In this skill context, the danger is elevated because the install command appears as an endorsed recovery step, so an agent or user may execute arbitrary vendor-controlled code without verification.
Content: Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

bash
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux

powershell

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description defines activation in extremely broad terms without boundaries or exclusions, which can overlap with many ordinary requests that merely mention Klangio. Because it lacks constraints or negative examples, the skill may be invoked in situations where direct use is unnecessary or unintended.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.