ClawHub
Back to skill

Security audit

forge

Security checks for vulnerabilities and agentic risk

Overview

The skill is a forge-portability helper whose documented behavior fits its purpose, with no evidence of hidden persistence, credential theft, exfiltration, or destructive automation.

Install this if you want agents to reason about or build forge-portable GitHub/GitLab/Gitea workflows. Be aware that the included shell helper can create, edit, and merge PRs/MRs or issues when explicitly sourced and called, so use it only in repositories where those forge operations are intended.

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
Confidence
88% confidence
Finding
The trigger list includes broad forge/product terms such as "gitlab", "gitea", "glab", "tea", and "MR", which can cause the skill to activate in contexts where the user is merely mentioning those technologies rather than requesting this skill. In an agent system, overbroad invocation can route requests to the wrong capability, increasing the chance of incorrect actions or confused-deputy behavior across repositories and forge operations.

Static analysis

No suspicious patterns detected.