ClawHub
Back to skill

Security audit

Project Quality Governance

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-governance helper with disclosed repository inspection and read-only validation behavior, and I found no hidden exfiltration, destructive action, or credential handling.

Install this if you want an agent to help structure engineering governance documentation. Before using it on an important repository, specify the target docs, whether edits are allowed, and which private paths or secrets are off-limits.

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
Confidence
82% confidence
Finding
The README shows a very broad natural-language invocation that can activate the skill for '审查并优化当前项目' without constraining scope, files, or permitted actions. In an agent setting, this can cause overbroad application of the skill to a repository, increasing the chance of unintended edits, excessive file access, or context overreach even though the surrounding documentation describes governance-focused behavior.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill enables implicit invocation while advertising a broad, generic purpose around structuring and validating engineering quality documentation. That combination can cause the agent to auto-select this skill in contexts beyond the author's intent, potentially letting repository content or user input trigger governance/refactoring behavior on authoritative documentation without clear user consent. In a documentation-governance skill, unintended invocation is more risky because it may modify specs, logs, or verification workflows that influence engineering and compliance decisions.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/validate-quality-docs.test.mjs:176