ClawHub
Back to skill

Security audit

Pandoc

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Pandoc document-conversion skill with a local helper script and no hidden persistence, credential handling, or remote execution behavior.

Install this only if you want Codex to run local pandoc conversions on files you specify. Review source and output paths before conversion, and be careful with advanced pandoc options such as filters, templates, resource paths, and media extraction because they can read or execute user-selected local resources through pandoc behavior.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises very broad triggers such as generic requests to 'transform', 'render to', or effectively any document conversion request, which can cause the agent to invoke this skill in situations where the user's intent is ambiguous. Over-broad routing increases the chance of inappropriate tool use, unintended file handling, or conversion of sensitive content without sufficient confirmation, especially because the skill can pass arbitrary extra arguments through to pandoc via the helper script.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.