ClawHub
Back to skill

Security audit

coding-agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight coding-agent/multilingual guidance package with no executable code, network behavior, credential handling, or persistence instructions.

Before installing, note that the skill may activate on generic coding-agent wording and it does not provide detailed operational safeguards for actually running background coding agents. Review any separate agent commands or workflows you choose to use with it, but this package itself does not request sensitive access or install executable behavior.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest-style `trigger_keywords` list contains only `coding` and `agent`, which are generic terms rather than specific invocation phrases. Without scope limits, exclusions, or concrete trigger examples, these broad keywords could cause unintended activation in ordinary development-related conversations.

Scope Creep

Low
Category
Excessive Agency
Content
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.