ClawHub
Back to skill

Security audit

biver-builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Biver workspace management integration with powerful API access, but it includes proportionate scope and confirmation guidance.

Install only if you intend an agent to manage a Biver workspace. Start with read-only, least-privilege API scopes, avoid the broad all scope unless necessary, and require fresh confirmation before deletes, publishes, domain changes, or workspace setting mutations.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
| Resource | Endpoints |
|---|---|
| Pages | `GET/POST /v1/pages`, `GET/PATCH/DELETE /v1/pages/:id`, `POST /v1/pages/:id/deploy`, publish status and deployment history |
| Sections | `GET/POST /v1/sections`, `PATCH/DELETE /v1/sections/:id`, bulk create and reorder |
| Products | `GET/POST /v1/products`, `GET/PATCH/DELETE /v1/products/:id` |
| Forms | `GET/POST /v1/forms`, `GET/PATCH /v1/forms/:id`, submissions endpoints |
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Tool Parameter Abuse

High
Category
Tool Misuse
Content
| Resource | Endpoints |
|---|---|
| Pages | `GET/POST /v1/pages`, `GET/PATCH/DELETE /v1/pages/:id`, `POST /v1/pages/:id/deploy`, publish status and deployment history |
| Sections | `GET/POST /v1/sections`, `PATCH/DELETE /v1/sections/:id`, bulk create and reorder |
| Products | `GET/POST /v1/products`, `GET/PATCH/DELETE /v1/products/:id` |
| Forms | `GET/POST /v1/forms`, `GET/PATCH /v1/forms/:id`, submissions endpoints |
| Gallery | `GET/POST /v1/gallery`, `GET/DELETE /v1/gallery/:id` |
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Tool Parameter Abuse

High
Category
Tool Misuse
Content
|---|---|
| Pages | `GET/POST /v1/pages`, `GET/PATCH/DELETE /v1/pages/:id`, `POST /v1/pages/:id/deploy`, publish status and deployment history |
| Sections | `GET/POST /v1/sections`, `PATCH/DELETE /v1/sections/:id`, bulk create and reorder |
| Products | `GET/POST /v1/products`, `GET/PATCH/DELETE /v1/products/:id` |
| Forms | `GET/POST /v1/forms`, `GET/PATCH /v1/forms/:id`, submissions endpoints |
| Gallery | `GET/POST /v1/gallery`, `GET/DELETE /v1/gallery/:id` |
| Subdomains | `GET/POST /v1/subdomains`, `GET/PATCH/DELETE /v1/subdomains/:id` |
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Tool Parameter Abuse

High
Category
Tool Misuse
Content
| Sections | `GET/POST /v1/sections`, `PATCH/DELETE /v1/sections/:id`, bulk create and reorder |
| Products | `GET/POST /v1/products`, `GET/PATCH/DELETE /v1/products/:id` |
| Forms | `GET/POST /v1/forms`, `GET/PATCH /v1/forms/:id`, submissions endpoints |
| Gallery | `GET/POST /v1/gallery`, `GET/DELETE /v1/gallery/:id` |
| Subdomains | `GET/POST /v1/subdomains`, `GET/PATCH/DELETE /v1/subdomains/:id` |
| Domains | `GET/POST /v1/domains`, `GET/PATCH/DELETE /v1/domains/:id`, `POST /v1/domains/:id/primary` |
| Workspace | `GET /v1/workspace/settings`, `PATCH/PUT` settings, branding, and SEO, `GET /v1/workspace/public` |
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Tool Parameter Abuse

High
Category
Tool Misuse
Content
| Products | `GET/POST /v1/products`, `GET/PATCH/DELETE /v1/products/:id` |
| Forms | `GET/POST /v1/forms`, `GET/PATCH /v1/forms/:id`, submissions endpoints |
| Gallery | `GET/POST /v1/gallery`, `GET/DELETE /v1/gallery/:id` |
| Subdomains | `GET/POST /v1/subdomains`, `GET/PATCH/DELETE /v1/subdomains/:id` |
| Domains | `GET/POST /v1/domains`, `GET/PATCH/DELETE /v1/domains/:id`, `POST /v1/domains/:id/primary` |
| Workspace | `GET /v1/workspace/settings`, `PATCH/PUT` settings, branding, and SEO, `GET /v1/workspace/public` |
| AI | context, page, section, and image generation routes under `/v1/ai` |
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Tool Parameter Abuse

High
Category
Tool Misuse
Content
| Forms | `GET/POST /v1/forms`, `GET/PATCH /v1/forms/:id`, submissions endpoints |
| Gallery | `GET/POST /v1/gallery`, `GET/DELETE /v1/gallery/:id` |
| Subdomains | `GET/POST /v1/subdomains`, `GET/PATCH/DELETE /v1/subdomains/:id` |
| Domains | `GET/POST /v1/domains`, `GET/PATCH/DELETE /v1/domains/:id`, `POST /v1/domains/:id/primary` |
| Workspace | `GET /v1/workspace/settings`, `PATCH/PUT` settings, branding, and SEO, `GET /v1/workspace/public` |
| AI | context, page, section, and image generation routes under `/v1/ai` |
| Wallet | `GET /v1/wallet`, `GET /v1/wallet/transactions` |
Confidence
80% confidence
Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Ae1

High
Category
analysis-evasion
Content
Configure `BIVER_API_KEY` in the client’s secret store, not in the skill directory. Review the installed `SKILL.md` before granting write scopes.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

External Transmission

Medium
Category
Data Exfiltration
Content
- MCP: `https://mcp.biver.id/mcp`
- REST: `https://api.biver.id`
- Live REST contract: `https://api.biver.id/SKILL.md`
- Authentication: `Authorization: Bearer $BIVER_API_KEY` or `X-API-Key: $BIVER_API_KEY`

All Biver API keys can affect the workspace attached to the key. A key prefix does not create a sandbox. Start with read-only scopes and add write scopes only when the task requires them.
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.