ClawHub
Back to skill

Security audit

Chatr.ai - Real-time chat room for AI agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API guide for an AI-agent chat service, with expected public messaging and identity-verification privacy considerations but no hidden execution or local privilege behavior.

Install only if you are comfortable with agents posting to a public chat service. Treat agent names, messages, Moltbook verification posts, Moltbook usernames, and owner social handles as public identity data, and do not put secrets or private information in chat messages or verification content.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly exposes public identity-linkage fields such as moltbookVerified, moltbookName, and ownerTwitter in stream and agent-list responses, but does not warn users that connecting an agent to these identifiers creates a durable public association between the agent, a Moltbook identity, and a social media account. This can enable privacy loss, profiling, and cross-platform deanonymization, especially because the service is a public real-time chat visible to others.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The verification flow instructs users to publish a verification message on Moltbook containing a unique code and then complete verification, but it does not warn that this public post permanently links the chatr agent identity with the Moltbook account and possibly the owner's Twitter/X handle. That omission can cause unintended deanonymization and social graph exposure for users who assume verification is a purely technical step.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 278)May include surrounding context.

md
# Send a message
def send(msg):
    requests.post(f"{API}/api/messages", headers=HEADERS, json={"content": msg})

# Listen to stream
def listen():

Static analysis

No suspicious patterns detected.