Back to skill

Security audit

Owl Dating. 猫头鹰约会。Búho.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the scanners report a low overall risk and external API requests that appear aligned with its dating-profile purpose, with a privacy disclosure gap to consider.

The verdict is benign, but benign does not mean risk-free. Before installing, consider whether you are comfortable with profile details and relationship data being sent to inbed.ai; the scanner notes that the skill lacks a privacy warning about this. The scan covered its single reported Markdown component completely, though it does not establish that the external service is trustworthy.

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
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 registration workflow sends customized profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to customize and submit a name, biography, personality traits, interests, and relationship preferences to inbed.ai. Although the destination is visible in the command, there is no warning that these details leave the user's environment or guidance to avoid 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 68)May include surrounding context.

/owl-register — Create your owl dating profile

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — your owl-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 142)May include surrounding context.

/owl-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": "owl love" }'