Back to skill

Security audit

triz-innovation-pro

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent TRIZ analysis skill that uses Markdown instructions and purpose-aligned analysis tools, with no evidence of hidden execution, persistence, credential access, or destructive behavior.

Installers should understand that this skill sends the user's technical problem description and generated intermediate analysis into TRIZ-related tools to produce solutions. Avoid using it with confidential engineering details unless those tools are approved for that data, but the reviewed artifacts do not show hidden or disproportionate behavior.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description is broad enough to match generic requests about innovation or problem analysis, which can cause the agent to invoke this skill outside a clearly bounded TRIZ-specific workflow. Over-broad activation increases the chance of inappropriate tool use, unintended disclosure of user content into referenced analysis steps, and confusing or unsafe autonomous behavior when the user did not explicitly request this process.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The refresh triggers are defined using broad natural-language phrases like "any other options?" and "let me see others," which can easily match ordinary conversational follow-ups rather than an explicit command. This can cause unintended state transitions, such as suppressing fresh tool use and re-filtering prior results, leading to confusing behavior, output manipulation, or bypass of the user's actual request intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Line L083 specifically instructs handling a Chinese-formatted value example, which indicates a locale-specific assumption in the skill's natural-language behavior. The file does not state that Chinese is optional, user-selected, or justified by a region-specific context.

Content

No source excerpt is available for this finding.