ClawHub
Back to skill

Security audit

content-strategy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a content-planning guide with limited, disclosed context-reading and no executable or persistent behavior.

Installers should expect this skill to help with content strategy and to read only the named product-marketing context files when available. If those files contain sensitive business information, review them before use; any CMS preview tokens mentioned by the guide should be handled through normal secret-management practices.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/headless-cms.md (reported line 93)May include surrounding context.

md
All major headless CMS platforms support draft previews:

- **Sanity**: Real-time preview with `useLiveQuery` or Presentation tool
- **Contentful**: Preview API (`preview.contentful.com`) with separate access token
- **Strapi**: Draft & Publish system with `status=draft` query parameter (v5; replaces v4's `publicationState`)

Set up a preview route in your frontend (e.g., `/api/preview`) that authenticates and renders draft content.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description contains broad trigger phrases like 'what should I write about,' 'content ideas,' and 'I don't know what to write,' which can cause the agent to activate this skill for many general writing or planning requests outside a narrowly defined content-strategy scope. Over-broad routing can misclassify user intent, suppress more appropriate skills, and increase the chance that this skill reads additional local context files unnecessarily.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The eval explicitly rewards activation on vague, casual phrasing ('what kind of content should we be creating?'), which can push the skill router toward over-broad matching and unintended invocation. Over-triggering is dangerous because it can hijack requests better handled by other skills, reduce routing precision, and create opportunities for prompt-confusion or policy bypass through ambiguous user input.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.