Security audit

PyOmniTS Usage Guide For Time Series Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a PyOmniTS documentation helper, but it also directs agents to clone outside research code and copy or rewrite it into a local PyOmniTS installation without enough safety controls.

Install only if you are comfortable treating this as an active code-adaptation helper, not just documentation. Before following its replication workflow, use a trusted repository, pin a reviewed commit, inspect copied files and dependencies, work in a branch or disposable environment, back up the PyOmniTS installation, and confirm every file write before applying changes.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:39
Finding: Unverified Third-Party Code Is Copied into an Executable Project
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill claims to provide documentation-oriented help, but later includes operational workflows that direct code import and project modification. This mismatch is dangerous because it can mislead users or higher-level agents into trusting the skill as low-risk reference material when it actually contains instructions that change local code and integrate external repositories.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill is presented as a documentation/helper skill, but it instructs the agent to perform repository cloning and direct file copying/rewriting into a local PyOmniTS installation. That expands the skill from informational guidance into making code and filesystem changes, which can import unreviewed third-party code and alter the user's environment without adequate safety boundaries.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The instructions tell the agent to copy or rewrite files inside ${PYOMNITS_PATH} without warning that these actions modify the user's local installation and may overwrite existing work. In this context, the lack of cautions, backups, or confirmation requirements increases the chance of unsafe changes, data loss, and integration of untrusted code into an execution environment.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.