Back to skill

Security audit

hd2-mod-authoring

Security checks for vulnerabilities and agentic risk

Overview

This skill is a detailed Helldivers 2 mod-authoring playbook whose file, memory, and tool-handling instructions are disclosed and aligned with that purpose.

Install this only if you want an agent to help with Helldivers 2 mod development and are comfortable with it editing local mod-manager files, packaging mods, reading game logs, and producing diagnostic game-memory dumps. Keep backups of hd2a_data.json and delete or review any Hd2ProjRecon dumps when finished.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description lists a long set of disparate activities ranging from mod authoring to malware vetting, but it does not define specific trigger phrases, boundaries, or exclusion conditions. In a manifest file, this kind of broad natural-language scope can cause unintended activation because many ordinary requests about Helldivers 2 mods or tools could appear to match.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This file states that the addon dumps game memory to disk and later discusses writing large table dumps as raw binary, but it does not warn users that memory dumps can contain sensitive or unexpected data. For markdown files, SQP-2 applies when descriptions omit warnings about behaviors that could affect user data, privacy, or system integrity.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 391)May include surrounding context.

md
independent — set them separately, and you can swap which icon goes on which
   round freely.

   - **Label is a RAW localisation string id**, not limited to the
     `modePresentation` catalog's offered labels. Any string in the game's
     `.strings` database resolves. To make the wheel read a specific word, find
     that word's id: extract the strings and read its `Key`:

Static analysis

No suspicious patterns detected.