Security audit

Ichimoku

Security checks for vulnerabilities and agentic risk

Overview

This skill should go to Review because it advertises an Ichimoku reference tool but mostly returns generic finance placeholder content.

Install only if you understand that this is not a reliable Ichimoku reference as packaged. It appears low-risk to the local system, but the content is mislabeled and could mislead finance or trading analysis unless corrected or treated as generic placeholder text.

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

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The script is benign and only outputs static text, with no hidden permissions or resource access. However, its substantive behavior does not match the declared purpose of an 'Ichimoku reference tool.' The content is largely placeholder-like and generic to finance/compliance/operations, and the formulas section contains generic financial formulas rather than Ichimoku-specific reference material. Because the primary purpose presented to the user is Ichimoku-specific guidance, but the actual delivered content is broad generic reference text, this is a material description-behavior mismatch.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest and heading describe a narrow 'Ichimoku reference tool' for finance contexts, which implies content focused on the Ichimoku indicator. However, the documented commands include generic finance topics like 'regulations', 'regulatory framework and compliance', and broad 'instruments' coverage, which extends beyond an obvious Ichimoku reference scope.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The description says this is a reference tool for working with Ichimoku, but the 'When to Use' section and commands such as 'risks', 'instruments', and 'checklist' describe wider operational and due-diligence assistance. That is broader than a straightforward Ichimoku reference utility and creates a semantic mismatch between claimed scope and documented behavior.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The header documentation explicitly markets the script as an Ichimoku reference tool, but the implementation serves unrelated generic finance text. In an agent-skill context, this mismatch is dangerous because agents may select the skill based on metadata and then propagate inaccurate or non-specialized output as authoritative domain guidance.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The tool presents itself as an Ichimoku-specific finance reference, but the exposed content is generic finance boilerplate and does not provide actual Ichimoku guidance. This creates a trust and integrity problem: users or downstream agents may rely on mislabeled output for financial workflows, leading to incorrect decisions, faulty automation, or unsafe compliance assumptions.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description and 'When to Use' section use generic phrases such as 'working with ichimoku,' 'troubleshooting ichimoku issues,' and 'need a checklist or guide,' but do not define specific invocation phrases, scope limits, or exclusion conditions. In a markdown skill description, this can make activation overly broad and increase the chance of unintended invocation in ordinary finance discussions.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.