ClawHub
Back to skill

Security audit

loop-builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a workflow-design aid that emphasizes user confirmation, bounded iteration, and explicit approval before risky actions.

Install this if you want a structured way to design bounded agent loops and reusable workflow artifacts. Review generated workflows before approving them, and be especially deliberate when a proposed loop would edit files, run commands, publish content, touch credentials, or create durable state.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

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 · references/skill-generation-contract.md (reported line 36)May include surrounding context.

md
2. Produce a Skill protocol draft.
3. Produce a temporary Prompt that can run the current task.
4. Wait for protocol approval.
5. Generate or modify Skill files only after explicit file-level approval.
6. Validate the package with the target repository's validator.
7. Request separate approval for installation, commit, push, or publication.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
### 1. Parse the Natural-Language Request

Accept a one-sentence request. Do not ask the user to fill a large form.
Extract what is already known:

- task and desired outcome;

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets public_language to en, which is a natural-language locale constraint. Under the policy, forcing a specific language without offering user choice or documenting justification is a reportable issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.