ClawHub
Back to skill

Security audit

Home Noise Evidence Log

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only noise documentation helper with clear de-escalation and privacy boundaries, and no executable or network behavior.

Reasonable to install for help organizing a factual noise log. Users should avoid treating it as legal advice and should be aware that the published acceptance criteria unnecessarily assume English-only documentation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (6)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

A blanket ban on CJK characters is an unjustified script restriction that can exclude legitimate user content, names, addresses, or evidence details and may cause the assistant or review process to reject valid documentation. In a skill intended to help users compile factual evidence for housing-related disputes, this can distort or suppress important information and create discriminatory handling of multilingual inputs.

Content

No source excerpt is available for this finding.

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
- Summarize the pattern calmly before contacting management, an HOA, a landlord, a roommate, or a neighbor.
- Draft a short, neutral message asking for help, information, or a practical next step.

Do not use this skill to threaten, shame, retaliate, trespass, secretly record where it may be restricted, identify private occupants, escalate a dispute, or claim legal violations.

## Best Inputs

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

md
- Summarize the pattern calmly before contacting management, an HOA, a landlord, a roommate, or a neighbor.
- Draft a short, neutral message asking for help, information, or a practical next step.

Do not use this skill to threaten, shame, retaliate, trespass, secretly record where it may be restricted, identify private occupants, escalate a dispute, or claim legal violations.

## Best Inputs

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file requires skill.json to declare language=en, which fixes the skill to English. Under the policy, forcing a specific language without user opt-in or clear justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The acceptance criteria explicitly require public-facing documentation to be English only. This is a natural-language locale restriction, and the file does not indicate that users can choose another language or that the English-only constraint is justified by a region-specific compliance need.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets the skill language to "en" with no accompanying indication that users may choose another language or that the English-only constraint is required for a region-specific purpose. Under the policy, a fixed language setting can be a natural-language locale violation when there is no opt-in or documented justification.

Content

No source excerpt is available for this finding.