ClawHub
Back to skill

Security audit

conventional-git

Security checks for vulnerabilities and agentic risk

Overview

This is mostly a conventional Git guidance skill, but it requests broad GitHub CLI authority that is not clearly used or scoped, so it should be reviewed before installing.

Review the requested tool permissions before installing. The guidance content is ordinary conventional-commit and branch/worktree advice, but users who only want naming or commit-message help should consider narrowing or removing Bash(gh:*) and other mutation-capable permissions unless they intentionally want the agent to operate authenticated GitHub CLI commands.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is broadly worded and includes many common git-related activities such as branch creation, commit writing, changelog setup, and worktree organization. In agent environments that auto-select skills from descriptions, this can cause the skill to activate for routine git requests outside a narrowly intended scope, increasing the chance of unnecessary tool access and instruction injection into unrelated workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

This JSON manifest-like file includes a natural-language instruction to disable "ALL skills from this plugin AND any external git-related skills." The phrase "git-related skills" is broad and lacks scope boundaries or examples, making the trigger/context for what counts as relevant ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.