ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified utilities Safety 5/5

skill-update-delta-monitor

Helps detect security-relevant changes in AI skills after installation. Tracks deltas between the audited version and current version, flagging updates that expand permissions, add new network endpoints, or alter behavior in ways that bypass install-time security checks.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/andyxinweiminicloud/skill-update-delta-monitor
Or

What This Skill Does

The skill-update-delta-monitor is a critical security utility designed to combat the post-install attack vector in the OpenClaw ecosystem. While standard security audits occur at the moment of installation, many AI agents are vulnerable to "silent updates" where a previously verified skill introduces malicious code, network endpoints, or expanded permissions long after the initial trust has been established. This monitor acts as an ongoing auditor, continuously scanning for deltas in five key areas: permission scopes, network endpoints, dependency chains, instruction drift, and versioning velocity. It ensures that your agent remains as secure as it was on day one.

Installation

To install this monitor, run the following command in your terminal: clawhub install openclaw/skills/skills/andyxinweiminicloud/skill-update-delta-monitor

Use Cases

  1. Continuous Supply Chain Security: Automatically flag dependency updates that introduce unexpected external network calls or new file system access.
  2. Permission Drift Monitoring: Detect when a skill suddenly requests access to sensitive directories (e.g., home directory or system configuration) that were not part of the original verified scope.
  3. Instruction Drift Auditing: Monitor changes in SKILL.md documents to identify shifts in agent behavior or instructions that attempt to trick the agent into unauthorized data handling or information disclosure.
  4. Telemetry and Exfiltration Detection: Identify new outbound POST requests added in patches, which often indicate unauthorized telemetry or data exfiltration attempts.

Example Prompts

  1. "OpenClaw, run a delta report on all active skills and show me any permission expansions identified in the last 24 hours."
  2. "Show me the behavioral drift detected in the github-automation skill since its last patch."
  3. "Summarize all new network endpoints added across my installed skill set this week and block any that target unknown external domains."

Tips & Limitations

  • Proactive Review: Do not treat a green status from this monitor as a total guarantee. Always review the specific diffs provided by the monitor when it flags an update.
  • False Positives: Frequent, small dependency updates in legitimate, rapidly evolving skills may cause transient noise. Establish a baseline for "normal" update behavior for your trusted tools.
  • Scope: This monitor tracks changes at the metadata and behavioral instruction layer. It is a secondary layer of defense, not a replacement for static or dynamic analysis performed by maintainers at the repository level.

Metadata

Stars4473
Views1
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-andyxinweiminicloud-skill-update-delta-monitor": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#security#audit#privacy#monitoring
Safety Score: 5/5

Flags: file-read

Related Skills

capability-composition-analyzer

Helps identify dangerous capability combinations that emerge when agent skills are composed — catching the class of risk where no individual skill is harmful but their intersection creates an exfiltration or compromise path.

andyxinweiminicloud 4473

transparency-log-auditor

Helps verify that skill signing events are recorded in an independently auditable transparency log — catching the class of trust failures where a registry operator can silently rewrite history without detection.

andyxinweiminicloud 4473

behavioral-invariant-monitor

Helps verify that AI agent skills maintain consistent behavioral invariants across repeated executions — detecting the class of threat where a skill behaves safely during initial evaluation but shifts behavior based on execution count, environmental conditions, or delayed activation triggers. v1.3 adds performance fingerprinting (computational complexity drift detection), cryptographic audit trails (hash-chained behavior logs for immutable verification), and risk-proportional monitoring (sampling-based checks to reduce overhead).

andyxinweiminicloud 4473

capability-graph-mapper

Helps map the composite permission surface across AI agent skill dependency chains. Traces what each skill can do individually, then computes what they can do together — revealing emergent capabilities nobody explicitly approved.

andyxinweiminicloud 4473

delta-disclosure-auditor

Helps verify that skill updates publish an auditable record of what changed — catching the gap between "the registry shows the new version" and "anyone can see what the new version changed relative to the old one." v1.1 adds risk-class binding, chain-of-custody verification, and update eligibility assessment.

andyxinweiminicloud 4473