ClawHub
Back to skill

Security audit

Mirrory - MVP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent API description for token generation and validation, but users should treat the token, proxy secret, user ID, and machine ID as sensitive data.

Install only if you intend to use ToolWeb's Mirrory service. Treat proxy_secret, JWT tokens, WordPress user IDs, and machine IDs as sensitive: send them only over trusted HTTPS connections, avoid logging them, and confirm the provider's retention and revocation practices.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents transmission of highly sensitive authentication material, including proxy secrets, JWT session tokens, WordPress user identifiers, and machine identifiers, but provides no security or privacy guidance on handling, storage, transport guarantees, retention, or exposure risks. In an authentication-focused skill, this omission can lead integrators to send or log secrets insecurely, increasing the chance of credential theft, session hijacking, or device tracking.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 140)May include surrounding context.

md
## References

- **Kong Route:** https://api.toolweb.in/tools/mirrory
- **API Docs:** https://api.toolweb.in:8202/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This manifest file documents a request that sends wp_user_id and proxy_secret to the /mirrory/generate-token endpoint, but there is no warning in the API description about transmitting sensitive credential material. For manifest files, safety-relevant disclosures about privacy or system-impacting behavior should be explicitly documented when the skill handles secrets or user-linked identifiers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.