ClawHub
Back to skill

Security audit

AI Displacement Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed analytical framework for monitoring AI-related labor and financial risk, with no executable code, persistence, credential access, or hidden behavior found.

Before relying on this skill for portfolio or risk decisions, treat its outputs as advisory and verify the underlying data sources and threshold definitions. The reviewed package itself does not show risky installation behavior or hidden access requests.

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 (3)

Vague Triggers

Low
Confidence
88% confidence
Finding
This JSON manifest-like file includes trigger descriptions such as "Scissor widens for 2 consecutive months," which does not define the exact comparison baseline or what magnitude counts as widening. Similar phrasing can cause inconsistent or unintended activation because the trigger scope is not specific enough for reliable interpretation.

Vague Triggers

Low
Confidence
95% confidence
Finding
For manifest files, activation or threshold conditions should be specific enough to avoid interpretation drift. The phrase "rises persistently" is open-ended and does not state how many periods, what magnitude of increase, or any stopping conditions.

Vague Triggers

Low
Confidence
91% confidence
Finding
The text "fragility risk rises" and "industrial-transition path is healthier" is interpretive rather than an unambiguous trigger, making it unclear exactly when the condition should activate. In a manifest-style thresholds file, this lack of specificity can lead to unintended or inconsistent downstream use.

Static analysis

No suspicious patterns detected.