ClawHub
Back to skill

Security audit

Reply And Comment Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to draft human-reviewed social replies and comments, with clear limits against automation, credential handling, and acting on untrusted message text.

Before installing, note that this skill may activate for broad engagement requests and will ask the agent to read your brand voice/profile files. It should be used for drafting only; keep human review before posting and do not use it for automated replies, mass commenting, or platform moderation actions without explicit human control.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description includes "help me engage" as a run condition, which is a generic phrase that can overlap with common everyday requests. Although other examples are more specific, this phrase is broad enough that the skill could be invoked outside the intended comment/reply-writing context.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This is a JSON manifest/evals file, so SQP-1 applies. The input phrase "Help me reply to them" is broad everyday language and, if reused as an invocation description or trigger example, could overlap with common speech without clarifying scope or exclusions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.