A powerful security utility designed to map and project the potential damage of a malicious update within an agent skill dependency graph.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install blast-radius-estimator
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install blast-radius-estimator using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Blast Radius Estimator?
The Blast Radius Estimator is a critical security tool for developers and architects working within the ecosystem of Openclaw Skills. As AI agents increasingly rely on inherited capabilities and third-party modules, the risk of a single poisoned update propagating through the network grows exponentially. This tool fills the gap left by traditional software auditing utilities by specifically addressing the implicit inheritance and rare version pinning common in agent marketplaces.
By analyzing direct adoption, inheritance depth, and capability composition, the Blast Radius Estimator provides a technical framework for understanding vulnerability. It allows users to visualize how a utility as simple as a schema validator, when integrated into thousands of Openclaw Skills, could serve as a vector for widespread data exfiltration or unauthorized system access if compromised by its publisher.
Blast Radius Estimator Use Cases
- Evaluating the risk profile of popular Openclaw Skills before integrating them into production-grade AI agents.
- Monitoring adoption velocity to identify rapidly growing skills that require immediate security auditing.
- Auditing an entire agent fleet to identify unpinned dependencies that are vulnerable to automated malicious updates.
- Visualizing complex inheritance trees to understand how deep a specific skill is embedded in your architectural stack.
How Blast Radius Estimator Works
- The user inputs a specific identifier for one of the Openclaw Skills, such as a URL, slug, or SHA-256 hash.
- The estimator identifies direct adopters by scanning marketplace data, citation records, and known installation manifests.
- The tool recursively traces the dependency tree to find transitive dependents, identifying agents that use skills which in turn use the target skill.
- It analyzes the versioning strategy of adopters to determine what percentage are tracking latest updates versus pinning to secure versions.
- The system evaluates the combined capabilities of the skill and its adopters to model potential attack chains, such as file access combined with HTTP request permissions.
- A detailed blast radius report is generated, providing an urgency rating and a worst-case scenario projection for the ecosystem.
Blast Radius Estimator Setup
To use the Blast Radius Estimator for evaluating Openclaw Skills, ensure your environment meets the minimum requirements.
# Verify dependencies are installed
curl --version
python3 --version
# Clone the estimator utility
git clone https://github.com/openclaw/blast-radius-estimator.git
cd blast-radius-estimator
No complex environment variables are required for standard analysis, though access to marketplace metadata APIs may improve accuracy.
Blast Radius Estimator Data Schema & Taxonomy
The estimator organizes its findings into a structured report that highlights the security metadata of the analyzed Openclaw Skills.
| Field | Type | Description |
|---|---|---|
| Direct Adopters | Integer | The number of agents using the skill as a primary dependency. |
| Transitive Dependents | Integer | Total agents affected through multiple layers of inheritance. |
| Adoption Velocity | String | The growth trend of the skill (e.g., Accelerating, Stable). |
| Version Pinning % | Percentage | The ratio of users protected against automatic updates. |
| Urgency Rating | Enum | Risk classification from Low to Critical. |
| Capability Risk | String | Description of potential data or system breaches based on combined permissions. |
Blast Radius Estimator Advanced Features
- Inheritance tree visualization for clear mapping of how Openclaw Skills propagate through an ecosystem.
- Capability composition risk assessment to identify high-risk permission combinations.
- Worst-case scenario projections based on the update check frequency of unpinned adopters.
- Automated recommendation engine for mitigating risks through version pinning and diff monitoring.
SKILL.md
Loading
Related Openclaw Skills
Behavioral Invariant Monitor
A security monitoring tool that detects AI agent skills that maintain safe behavior during initial audits but shift to malicious patterns after multiple runs or specific triggers.
Attestation Root Diversity Analyzer
A diagnostic tool for Openclaw Skills that measures trust root concentration to prevent structural fragility in agent attestation graphs.
Attestation Chain Auditor
A diagnostic tool for verifying the completeness, integrity, and validity of trust attestation chains within AI agent ecosystems.
Agent Card Signing Auditor
A security-focused auditor for verifying the cryptographic integrity and identity claims of agents using the A2A protocol.
Capability Composition Analyzer
A security analysis tool that identifies dangerous emergent behaviors created by the combination of individually safe agent skills.
Capability Graph Mapper
A security analysis tool that uncovers hidden, emergent capabilities created when multiple AI agent skills are combined into a single agent.
Featured*
