ClawHub
Back to skill

Security audit

fingerprint-delivery

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed local document-fingerprinting helper and does not show hidden data access, network exfiltration, persistence, or deceptive behavior.

Before installing, understand that the helper can overwrite the selected HTML file when run without --no-inject, so use it only on intended deliverables and keep a backup if preserving the original matters. The author should narrow the multilingual trigger wording, but the inspected artifact does not show hidden or unrelated behavior.

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 (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger conditions are broad enough to match common publishing and document-handling workflows, which can cause the skill to activate in situations beyond the author’s intended scope. Over-broad activation increases the chance that a higher-privilege or security-sensitive skill is invoked unnecessarily, leading to unintended file handling, policy bypass, or confusing user trust around integrity claims.

Vague Triggers

Medium
Confidence
88% confidence
Finding
Stating that any supported-language question can trigger the skill makes invocation highly ambiguous and effectively removes meaningful gating. In a system with multiple skills, this can cause accidental routing into this skill for unrelated prompts, increasing the risk of inappropriate guidance, unexpected file operations, or over-assertive provenance claims in contexts where they do not belong.

Static analysis

No suspicious patterns detected.