ClawHub
Back to skill

Security audit

/all-green

Security checks for vulnerabilities and agentic risk

Overview

This skill automates a GitHub PR readiness loop, but its requested GitHub and local-code actions are disclosed, purpose-aligned, and guarded by user approval points.

Install only if you want Codex to actively manage PR publication, review feedback, CI investigation, local fixes, commits, and pushes. Confirm the intended files and branch before publication, and give explicit permission only for actions you want, especially pushing fixes or posting anything on GitHub.

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

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says to use the skill when the user 'asks to create/open a PR and then monitor it' or 'wants an existing PR watched and fixed,' which are broad natural-language triggers rather than a tight invocation scope. Although '/all-green' is specific, the additional generic phrases increase the chance of unintended activation from ordinary PR-related requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.