Security audit

Encodian

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Encodian connector, but it includes under-controlled first-time setup and document-handling instructions that deserve review before installation.

Install only if you are comfortable with OOMOL brokering Encodian access and processing the documents you provide. Review or manually install the oo CLI instead of letting an agent run remote shell install commands, and require explicit approval before actions that unlock, extract, encrypt, or otherwise transform PDFs.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

External Script Fetching

High

Category: Supply Chain
Confidence: 97% confidence
Finding: The skill instructs the agent to install software by piping a remote script directly into bash. This is a classic supply-chain and remote code execution risk: if the remote host, transport, or script is compromised, arbitrary code runs immediately on the user's machine with no review.
Content: Scanner excerpt · SKILL.md (reported line 59)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: 95% confidence
Finding: The trigger language says to use this skill for ANY Encodian request, which is overly broad and can cause the agent to route all Encodian-related tasks through this skill without considering narrower or safer alternatives. While not directly exploitable on its own, broad activation increases the chance of unnecessary invocation of powerful actions and amplifies the effect of other safety issues in the skill.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill asserts that untagged actions are read-only, but several untagged actions actually transform or decrypt user documents and return modified output. This can mislead an agent into skipping confirmation or safety checks for operations that materially alter sensitive content, increasing the risk of unintended data handling or disclosure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.