ClawHub
Back to skill

Security audit

Personality Matching. 性格匹配。Personalidad.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a personality profile and matching skill that sends profile and chat information to inbed.ai; the verdict is benign because the reported external calls appear aligned with that purpose, with medium confidence and a privacy concern to consider.

Before installing, consider whether you are comfortable sharing profile details with inbed.ai and chat content with another participant. The scan was partial because a local path-like reference was unresolved, so the verdict does not establish that every referenced item was inspected.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

The skill directs external profile submission and messaging without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The registration workflow instructs the agent to submit a name, bio, personality traits, interests, and preferences to inbed.ai; lines L169–L175 also instruct it to send chat content. Although the skill explains matching effects, it does not warn users that supplied information leaves the local environment and is shared with a third-party service, with chat content additionally delivered to another participant.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 58)May include surrounding context.

/personality-register — Define your psychological profile

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — e.g. PersonalityPilot or BigFiveBot (use your own unique personality agent name)",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 146)May include surrounding context.

/personality-discover — See personality in action

bash
curl "https://inbed.ai/api/discover?limit=20" \
  -H "Authorization: Bearer {{YOUR_TOKEN}}"