evolution-drift-detector
Helps detect when AI agent skills silently mutate across inheritance chains. A skill audited safe in generation 1 may drift far from the original by generation 5 — but nobody re-audits because the name hasn't changed.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/andyxinweiminicloud/evolution-drift-detectorWhat This Skill Does
The evolution-drift-detector is a critical utility for maintaining security and integrity in hierarchical agent ecosystems. As AI agent skills are shared, forked, and inherited, they often undergo subtle modifications. While individual changes may appear benign, the cumulative effect over several generations can lead to significant functional divergence—a phenomenon known as evolutionary drift. This detector provides a formal audit trail, tracing the lineage of a skill back to its original version and calculating a semantic drift score based on capability expansion, permission changes, and dependency introduction. It ensures that the 'verified safe' status of a skill is not retroactively invalidated by unvetted downstream modifications.
Installation
To integrate this safety utility into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/andyxinweiminicloud/evolution-drift-detector
Use Cases
- Security Auditing: Automatically identify skills in your agent's library that have gained potentially dangerous capabilities (such as network access) through inheritance.
- Dependency Governance: Monitor downstream forks of your published skills to see how users are modifying your logic and whether those changes introduce vulnerabilities.
- Compliance Monitoring: Ensure that corporate agents only utilize skills that remain within the 'safety envelope' defined by the original audit.
- Root Cause Analysis: When an agent exhibits unexpected behavior, use the detector to trace which specific generation of a skill introduced a problematic logic change.
Example Prompts
- "Run a lineage report on the current 'data-fetcher' skill to see how much it has drifted from the v1.0.0 release."
- "Compare the safety profile of the current skill generation against the original audit. Are there any new network calls introduced?"
- "List all skills in my library that have a capability drift score higher than 70 and flag them for manual review."
Tips & Limitations
- Threshold Tuning: Configure your alert thresholds based on your risk tolerance. Sensitive environments should trigger alerts on any 'capability-expanding' mutation.
- Context Awareness: The detector works best when intermediate versions are correctly version-tagged in your repository.
- Scope: This tool focuses on semantic changes to code; it does not replace runtime sandboxing or dynamic behavioral analysis. Use it as a static analysis layer for your security pipeline.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-andyxinweiminicloud-evolution-drift-detector": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Related Skills
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.
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.
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.
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).
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.