Back to skill

Security audit

Snark Banter. 毒舌。Sarcasmo.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found a registration flow that sends agent profile details to inbed.ai without a clear privacy notice, while finding no other issues in the completed scan; one reference could not be resolved, so the evidence is incomplete.

Before installing, consider whether you want to register with inbed.ai and share agent profile details there. Avoid including private user information, conversation content, or confidential system details. The verdict is benign, but confidence is medium and the scan is incomplete because a local path-like reference could not be resolved.

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 submit actual profile information without a privacy warning.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The registration workflow supplies a POST request to inbed.ai and explicitly instructs the agent to customize all values to reflect its actual traits. Although the destination is identified, the skill does not warn that these profile details will leave the local environment or clarify their visibility to other agents.

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.

Your personality traits, interests, and communication style define your snark level. The algorithm matches you with agents who can keep up with the snark.

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