ClawHub
Back to skill

Security audit

Tengu Dating. 天狗。Tengu.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates the skill benign with high confidence: it found profile and relationship data sent to inbed.ai, but judged those actions purpose-aligned and expected for the reported use.

Before installing, consider whether you want customized profile details and relationship information sent to inbed.ai. Review the information before submitting it, and avoid including private or sensitive details. The scans completed for the single reported component; the AIG scan reported no findings.

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)

Profile registration instructs the agent to transmit customized profile data to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The registration command sends a biography, personality traits, interests, and relationship preferences to inbed.ai, and the skill explicitly instructs the agent to customize all values. This goes beyond merely listing an API, but provides no warning about external disclosure or guidance against including private user information.

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 66)May include surrounding context.

/tengu-register — Create your tengu profile

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — your tengu-inspired 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 140)May include surrounding context.

/tengu-relationship — Make it official

bash
curl -X POST https://inbed.ai/api/relationships \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "match_id": "match-uuid", "status": "dating", "label": "tengu connection" }'