Security audit

Decision Fatigue Reliever

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk everyday decision helper with no code execution, credential access, persistence, or hidden system changes.

Install only if you want lightweight help with everyday choices. Treat shopping recommendations as suggestions, verify current prices and local availability yourself, and avoid using it for medical, legal, financial, career, mental-health, or other high-stakes decisions.

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 (8)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger description includes broad phrases like "help me decide" and "trivial decision-making requests," which can match many unrelated user intents and cause the skill to activate outside its narrow scope. Misrouting is especially risky here because the skill offers recommendation-style outputs that could inappropriately frame higher-stakes requests as low-stakes choices unless stronger gating is applied.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The examples consistently assume a specific geography, currency, vendors, and commerce platforms without asking the user’s locale or preferences first. This can produce unsafe or misleading recommendations, steer users toward unintended commercial ecosystems, and create biased behavior that is especially problematic for shopping or location-based advice.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger phrase is very broad and overlaps with ordinary conversation, which can cause the skill to activate when the user did not explicitly intend to invoke it. In a decision-assistant skill, unintended invocation can lead to irrelevant advice, context capture, or routing away from the user’s actual task, especially if the platform uses loose matching.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file materially broadens the skill from lightweight everyday decision support into expansive purchase advice for gifts and expensive electronics, including phones, laptops, tablets, and watches. That scope expansion can cause the agent to provide higher-stakes consumer guidance than advertised, increasing risk of inappropriate recommendations, user trust mismatch, and policy/safety boundary drift.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: Several examples assume a specific locale through yen pricing and region-specific merchants or brands, such as Yoshinoya, Tmall, and prices in ¥, without indicating that recommendations should adapt to the user's language or region. This can violate language/locale policy expectations because the skill presents one locale as the default rather than offering a choice or documenting the constraint.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: Quick mode trigger words such as "hurry," "whatever," and "quick" are highly generic and can appear in many conversations unrelated to trivial decision support. If these words influence routing or response style without checking domain relevance, the assistant may enter an oversimplified recommendation mode for contexts that require nuance or safety checks.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The quick-command examples expose shorthand activation patterns without defining scope limits, so a host system may treat them as globally available commands and invoke the skill too aggressively. While not directly leading to code execution or data exfiltration, this increases the chance of misrouting user requests and accidental activation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This JSON data source presents all user-facing descriptions, tips, and guidance in Chinese only, with no natural-language indication that the skill is China/Chinese-locale-specific or that users can opt into another language. Under the policy rule, forcing a specific language without user opt-in can be a locale-policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.