ClawHub
Back to skill

Security audit

Release Feature Watcher

Security checks for vulnerabilities and agentic risk

Overview

This skill creates scheduled watchers for technical releases, and its persistent cron behavior is disclosed, scoped, and designed to clean itself up.

Before installing, users should understand that this skill may create scheduled cron watchers that periodically check external technical sources and write small local watcher configs. Use it only for specific technical readiness conditions, review created job IDs and expiry dates, and remove watchers when they are no longer needed.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to inspect sources, create cron jobs, verify jobs, and optionally read/write watcher config and registry files, which implies network and file access. Because the manifest declares no explicit tool scope or permissions, the runtime may grant broader capabilities than intended or leave operators unable to enforce least privilege. In a watcher skill, this increases risk because it repeatedly accesses external URLs and local state over time.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% 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 55)May include surrounding context.

md
5. **Silence rule**: no update unless actionable or broken.
6. **Cleanup rule**: remove when done, expire when stale.

If you cannot state the condition precisely, do not create a watcher yet. Ask one concise clarifying question or park the resource instead.

## Watcher Classes

Static analysis

No suspicious patterns detected.