ClawHub
Back to skill

Security audit

press-coverage-page-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple writing and page-structure guide for press coverage pages, with no hidden execution, persistence, or high-impact authority.

Installers should expect this skill to guide website/page copy and structure for press coverage. Review the broad invocation wording if precise skill routing matters, and be aware it may read existing project context files if present to tailor messaging.

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 whenever the user wants to create a press coverage page and lists several broad phrases such as "press coverage" and "media mentions" without clear exclusion boundaries beyond one PR-related case. In a markdown/manifest context, this can cause unintended invocation for general discussion of media coverage rather than explicit page-generation requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.