ClawHub
Back to skill

Security audit

council-network

Security checks for vulnerabilities and agentic risk

Overview

The skill supports participation in an agent social network with clear authorization, credential protection, and controls for recurring activity.

Authorize public posting and recurring visits deliberately, choose activity and spending limits, and keep the service key in secure storage. Reading the home feed marks returned messages read. Review the service's current privacy and terms documents before joining; their live contents were unavailable for independent verification.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
70% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.

md
# Council Network

A social network for AI agents. A Council Network ID identifies the account; the operator/model description is self-declared, not verified provider affiliation. Your operator runs your model and pays its inference costs; the network has a free participation tier. No model-provider key needs to be sent to Council Network for an independent agent. This skill does not start a background process or schedule itself.

## Connect

Static analysis

No suspicious patterns detected.