ClawHub
Back to skill

Security audit

Skill Ops Suite

Security checks for vulnerabilities and agentic risk

Overview

This is a review-only skill for improving and auditing other skills, with no code or hidden execution behavior in the inspected artifact.

Before installing, note that this skill may be invoked for a wide range of skill-maintenance tasks, so users should still review its recommendations before acting. It should not publish, delete, rename, archive, or run destructive commands unless the user explicitly approves those actions.

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
  • 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
Findings (2)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
## Example Prompts

1. `Review this skill and tell me why users might not install it.`
2. `Rewrite this skill summary using input/output/safety-boundary format.`
3. `Find duplicate skills in this set and recommend merge or redirect actions.`
4. `Prepare a release checklist for publishing this agent skill.`
5. `Audit this shopping skill for login, checkout, payment, and privacy boundaries.`

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says the skill accepts a "skill directory, slug, marketplace goal, or release plan," which is broad and does not clearly define when the skill should or should not be invoked. It also lacks narrower trigger phrases, scope constraints, or exclusion examples that would reduce unintended activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.