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 skill files only as part of its stated purpose.

Review any generated skill before installing it, especially allowed-tools, hooks, shell injection, and persistence-related settings. This package itself is plain instructional Markdown and does not contain executable install logic or hidden authority grants.

SkillSpector

Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Self-Modification

High
Category
Rogue Agent
Content
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.
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.

Static analysis

No suspicious patterns detected.