Back to skill

Security audit

OPM Modeler

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only OPM modeling skill with no code execution or data access; its main caveats are broad activation wording and Spanish-oriented modeling conventions.

Installers should expect this skill to steer conversations toward formal OPM modeling and may want tighter trigger wording if they often discuss generic agents, instruments, or system diagrams outside OPM. Users who prefer English output should ask for English OPL explicitly.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description is extremely broad and includes many generic terms such as 'model', 'validate', 'system diagram', and methodology-specific acronyms that may appear in unrelated conversations. This can cause unintended invocation of the skill, leading the agent to load irrelevant instructions and alter response behavior in contexts where OPM modeling was not requested.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill content imposes Spanish-language conventions and prioritizes Spanish OPL templates without clear user opt-in, which can override user language expectations or higher-level assistant behavior. While not directly enabling code execution or data exfiltration, it can cause instruction-following drift, reduce usability, and create prompt-conflict behavior in multilingual contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This file explicitly sets the artifact language to Spanish and the body consistently prescribes Spanish realizations in multiple sections, but it does not offer an opt-in language choice. Under the language/locale policy rule, forcing a specific language without user choice is a natural-language policy concern unless the constraint is clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document states that OPM's textual modality uses 'OPL sentences in English subset,' which imposes a specific language in the skill content. Because no alternative language option, opt-in, or justification for the locale restriction is provided in the file, this appears to violate the language/locale policy criterion.

Content

No source excerpt is available for this finding.