Back to skill

Security audit

Crane Hook Annotation

Security checks for vulnerabilities and agentic risk

Overview

The skill’s goal is coherent, but its main documented command runs a missing PowerShell script with execution policy bypassed, so users cannot verify what would execute.

Only install or use this after the missing annotation script is supplied from a trusted source and reviewed. Prefer commands that do not bypass PowerShell execution policy, and run the skill only on intended image folders with an explicit output directory.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Note
Location
SKILL.md:21
Finding

PowerShell Commands Disable Execution-Policy Enforcement

Content
View full analysis
Remediation
View remediation
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
93% confidence
Finding

The skill enables implicit invocation but does not define narrow activation constraints, so an agent may auto-select it in situations broader than intended. Because this skill performs batch image processing and exports modified images and coordinate metadata, unintended invocation could cause unauthorized processing of user files or unexpected data handling without clear user intent.

Content

No source excerpt is available for this finding.