Security audit

Auto Insight Engine 5ec95c

Security checks for vulnerabilities and agentic risk

Overview

This skill is low-capability, but its topic and triggers are mixed across unrelated products, so users should review it before relying on it.

Review this skill carefully before installing. It does not appear to execute code or request sensitive access, but its instructions combine unrelated Insight topics and broad triggers, so it may activate in the wrong context or give misleading guidance.

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 (4)

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill claims to teach Revit Insight, but the embedded sources and merged content reference unrelated domains such as EEG headsets, Cognex In-Sight software, and autonomous cameras. This mismatch can cause the agent to invoke the skill in the wrong context and provide misleading or unsafe guidance based on irrelevant material, increasing the risk of incorrect actions or user deception.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger conditions are broad and ambiguous, including generic terms like "revit" and a catch-all request for related help. This can cause accidental invocation in unrelated conversations, exposing users to irrelevant or incorrect instructions and making prompt routing easier to abuse.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The merged section introduces another vague trigger set with broad help language and weak scope boundaries. Because it references a different topic variant, it further increases the chance of misrouting user requests and activating the skill for unrelated product or software discussions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file forces a single language for the skill's metadata and usage instructions, but does not indicate that the language choice is optional or justified by a region-specific requirement. This can violate language-choice policy when users are not given an opt-in or alternative locale.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.