ClawHub
Back to skill

Security audit

PDF.co

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for PDF.co work, but its setup instructions include unaudited remote installer execution and some state-changing PDF operations are not clearly gated.

Review this skill before installing. Use it only if you trust OOMOL’s CLI distribution and PDF.co connector path, and require explicit approval before installing the CLI, signing in, connecting PDF.co, or running any action that creates files, transforms documents, uploads content, or consumes credits.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (2)

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The skill instructs the agent to install the CLI by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a direct remote-code-execution path: if the host, transport, distribution channel, or script is compromised, arbitrary code will run on the user's machine without review or integrity verification.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description says to use this skill for "ANY PDF.co request" and "whenever a task involves PDF.co," which is an overly broad trigger that can cause the agent to invoke the skill in situations where a narrower or safer path would be more appropriate. Broad routing increases the chance of unintended tool use, including write-capable operations, and reduces the opportunity for task-specific safety checks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.