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

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.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/andyxinweiminicloud/delta-disclosure-auditor
Or

What This Skill Does

The delta-disclosure-auditor is a critical utility for OpenClaw users who prioritize supply chain security and continuous monitoring. In the current ecosystem, skill updates often fail to communicate exactly what changed, creating a 'transparency gap' that forces users to choose between blind trust and the expensive, impractical process of re-executing full audits on every update. This auditor bridges that gap by enforcing machine-readable disclosures.

Version 1.1 significantly advances these capabilities. It now integrates risk-class binding, ensuring that changes are scrutinized based on the skill’s potential impact (e.g., a credential handler is held to higher standards than a simple UI formatter). It introduces chain-of-custody verification, using cryptographic hashes to ensure that every update history is immutable and verifiable. Finally, it implements update eligibility assessment, effectively turning transparency into a requirement for automated updates. By auditing capability declarations, dependency changes, and behavioral scopes, this skill ensures you aren't just notified that a skill changed, but exactly how its risk profile evolved.

Installation

To add the delta-disclosure-auditor to your agent environment, run the following command in your terminal:

clawhub install openclaw/skills/skills/andyxinweiminicloud/delta-disclosure-auditor

Once installed, the auditor automatically hooks into your package management lifecycle to intercept and validate update metadata.

Use Cases

  • Continuous Security Monitoring: Automatically audit third-party skills to detect unauthorized changes in outbound network endpoints or file access permissions before auto-updating.
  • Enterprise Compliance: Ensure all installed skills meet specific organizational risk-class binding requirements.
  • Supply Chain Integrity: Verify the chain-of-custody for critical infrastructure skills, ensuring that every version transition is cryptographically linked to the previous authorized state.

Example Prompts

  1. "Audit the latest update for the 'file-transfer-pro' skill and report any undocumented changes in its dependency tree or file system access permissions."
  2. "Check if the update to 'api-gateway-auth' satisfies the chain-of-custody requirements and show me the risk-class binding report."
  3. "List all skills currently installed that lack proper delta disclosure and mark them as ineligible for auto-updates until the publisher provides a full change manifest."

Tips & Limitations

  • Best Practice: Always treat 'ineligible' status as a warning signal. If a skill developer refuses to provide a delta disclosure, they may be obscuring supply chain vulnerabilities.
  • Risk-Class Tuning: Customize your risk thresholds to ensure that lower-risk skills don't overwhelm your workflow with notifications, while high-risk skills receive maximum scrutiny.
  • Limitation: The auditor is most effective when publishers adopt the OpenClaw delta disclosure standard. While it can infer gaps in non-compliant skills, it cannot retroactively create disclosure logs for legacy versions that lack historical metadata.

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-delta-disclosure-auditor": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#security#auditing#supply-chain#compliance#transparency
Safety Score: 5/5

Flags: code-execution

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

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.

andyxinweiminicloud 4473