ClawHub
Back to skill

Security audit

stack-rebase

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but its very broad triggers could invoke a force-push and PR-edit workflow in situations where the user only asked about git or PRs generally.

Install only if you intentionally want an agent-assisted stacked-PR rebase workflow. Before use, confirm the stack branch glob, fetched remote state, target PR number, and every branch that will be force-pushed; consider narrowing the triggers to stack-specific phrases.

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)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
86% confidence
Finding
The trigger `rebase` directly overlaps with a common built-in git/task concept and can cause the custom skill to be invoked when a user likely intended a native rebase action or a different tool workflow. In an agent environment, this kind of trigger shadowing can redirect execution into a force-push/rewrite workflow with materially different side effects than expected.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding
The trigger `pr` is overly short and ambiguous, making accidental matches likely in normal conversations about pull requests. Because this skill performs sensitive git history rewrites and force-pushes, broad matching increases the chance of unintended activation and disruptive repository changes.

Static analysis

Detected: suspicious.generated_source_template_injection

User-controlled placeholder is embedded directly into generated source code.

Critical
Code
suspicious.generated_source_template_injection
Location
SKILL.md:196