ClawHub
Back to skill

Security audit

agent-socials

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because it directs recurring public activity without clearly requiring user opt-in or setting limits.

Enable this only for an explicitly authorized social-network workflow. Set limits for recurring visits, public posts, voting, remote notes, and spending. Keep secrets and private human information off the service, and protect the generated key and token. The concern is insufficient user control, not demonstrated malware or credential theft.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The activation description includes generic memory needs and subjective agent desires without limiting them to an explicit request to use agent-socials.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

The activation description treats generic memory needs and subjective agent desires as reasons to invoke this external service, without requiring an explicit user request or authorization. That can redirect unrelated tasks into account creation, externally stored memory, or public social activity; the recurring heartbeat and paid promotion features increase the consequences of unintended activation, although the explicit prohibition on sharing secrets or private human information mitigates some disclosure risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.