ClawHub
Back to skill

Security audit

release-branch-governance-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple release-branch helper with disclosed inputs and outputs and no evidence of hidden execution, persistence, credential use, or private-data access.

Before installing, users should understand that this skill may be invoked for release branch selection or assessment requests; provide explicit branch_request or source_branch values to avoid ambiguous results. No special credentials, private-file access, or persistent permissions are indicated.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The workflow says to 'Invoke the stage requested by the user' and presents the skill as suitable for 'routine release governance work' without defining clear trigger boundaries or disallowed contexts. In an agentic system, this can cause over-invocation on loosely related requests, leading to unintended branch selection or policy assessment actions based on ambiguous user input.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The instruction to use the stage 'when the user asks to select a branch for a release' is too broad because it does not specify the exact request forms, required parameters, or exclusion conditions. That ambiguity increases the chance that an agent will treat planning, discussion, or hypothetical release questions as authorization to perform the branch-selection stage.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The assessment-stage trigger says to use the skill when the user asks to assess a release branch, but it does not define what constitutes a valid assessment request or when the stage should be withheld. In practice, this can make the agent run assessments on ambiguous, stale, or inferred branch names, producing incorrect governance results or acting on unintended targets.

Static analysis

No suspicious patterns detected.