ClawHub
Back to skill

Security audit

Commit Poetry

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only creative skill that turns git history into poetry, with no evidence of hidden code execution, persistence, network access, or credential handling.

Before installing, be aware that the skill works from git history, so generated poems may reflect private commit messages, branch names, tags, or file-history context. It does not show evidence of sending that data elsewhere or running code.

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 (1)

Vague Triggers

Low
Confidence
95% confidence
Finding
The 'When to Invoke' section lists general situations like 'Friday afternoon,' 'When you need a laugh,' and 'After a production incident' without defining explicit activation phrases, boundaries, or exclusion conditions. In a markdown skill description, this kind of broad natural-language trigger guidance can overlap with common conversation and lead to unintended invocation.

Static analysis

No suspicious patterns detected.