ClawHub
Back to skill

Security audit

skill-creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed skill-authoring helper that creates local Claude Code skill files and includes reasonable guardrails for review and overwrites.

Review any skill this generator creates before saving or installing it, especially any allowed-tools grants, hooks, dynamic command injection, or actions that change external systems. The generator itself is coherent and purpose-aligned.

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 · reference.md (reported line 55)May include surrounding context.

md
The skill listing has a context budget (~1% of the context window; least-used skills lose their descriptions first when it overflows). `/doctor` estimates the listing's cost. `skillOverrides` in settings can force a skill to `name-only` or `off` without editing its file.

## Lifecycle notes that change how you write skills

- Once invoked, the rendered body stays in context for the rest of the session and is not re-read — write **standing instructions**, not one-time steps. Re-invocation with identical content is deduped (v2.1.202+).
- After auto-compaction, each invoked skill is re-attached with its first 5,000 tokens, under a 25,000-token shared budget, most-recent first — huge skills lose their tails; re-invoke after compaction if a skill matters.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'When to Use' section lists trigger examples like 'I want a skill that does X' and 'Build me a slash command for Y', which are generic phrases a user might say in many contexts. The file does not provide explicit boundaries or negative examples clarifying when this skill should activate versus when a normal conversational response is appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.