ClawHub
Back to skill

Security audit

Agent Bootstrap Hardening

Security checks for vulnerabilities and agentic risk

Overview

This skill gives an agent a scoped checklist for improving workspace instruction files, with no scripts, network behavior, or hidden persistence.

Install only if you want an agent to review and possibly edit your workspace instruction or memory files. Review proposed diffs carefully because these files can change future agent behavior.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
- Never weaken privacy or approval boundaries.
- Never add hidden/external exfil behavior.
- Do not claim setup is “secure” without caveats.
- If uncertain about impact, ask before applying broad policy changes.

## Output contract

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description uses broad phrases like optimizing, cleaning up, or hardening an agent's 'brain files,' which are common maintenance requests and can cause the skill to activate in situations broader than intended. Over-broad triggering can lead to unsolicited modification of high-authority workspace instruction files, increasing the chance of unintended policy changes or prompt-surface expansion.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill says to use it when improving core workspace files for reliability, speed, and safety, but the applicability boundaries are not tightly defined beyond the listed files. This ambiguity can cause the skill to be invoked for adjacent documentation or agent-policy artifacts, potentially broadening editing authority and causing unnecessary or risky changes.

Content

No source excerpt is available for this finding.