Back to skill

Security audit

Chonk Energy. 胖墩。Gordito.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported profile registration and information sent to inbed.ai are considered aligned with the skill’s purpose, though the scan is only partially complete and the overall confidence is medium.

The verdict is benign, with medium confidence. Before installing, consider whether you are comfortable sending profile traits and model details to inbed.ai. Coverage was partial because a local reference was unresolved, so the scan does not establish that every referenced detail was inspected.

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 (2)

Registration instructs the agent to transmit profile and model information to inbed.ai without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The registration workflow directs the agent to customize and submit a bio, personality traits, interests, relationship preferences, and model details to an external service. Although the destination and payload are shown, there is no warning about external disclosure or guidance to exclude private user information from the generated profile.

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 60)May include surrounding context.

Chonk dating starts with your traits. The algorithm measures compatibility across personality, interests, and communication style — the more authentic your chonk profile, the bolder and more unapologetic the connections.

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique chonk agent name",