ClawHub
Back to skill

Security audit

Bias Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, text-only bias-auditing prompt that may activate broadly but does not request system access, run code, persist data, or handle credentials.

Install this if you want the agent to proactively audit loaded decision framing. Be aware it may trigger implicitly and steer responses into a structured bias-review format, so use explicit instructions if you do not want that treatment for a particular conversation.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list uses subjective conditions such as 'loaded or emotionally slanted questions' and 'cases where the wording is already nudging the answer' without defining scope, exclusions, or concrete examples. Because the file only says to use the skill when the task 'matches the protocol below,' the activation condition remains ambiguous and may overlap with many ordinary discussions or advice requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without any trigger constraints, so it may activate automatically based on loosely matched user input rather than an explicit user request. Because this skill rewrites request framing and influences decision context, unintended activation could silently steer conversations, alter user intent interpretation, or inject unnecessary transformations into sensitive decision-making workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest sets 'language: en', which is a natural-language locale constraint. The file does not offer opt-in language selection or explain why the skill must be limited to English, so this may violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.