Back to skill

Security audit

SEO Content QA

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill suspicious because its workflow reportedly sends draft structured data to external validators without warning users about possible disclosure; confidence is medium and the scan is incomplete.

Before installing, consider whether you may use it on unpublished or sensitive content. The reported workflow could send draft structured data to third-party validators without warning; prefer local validation or review and redact the data before any external submission. The scan is incomplete because a referenced local path was missing, so the results do not establish that all relevant material was assessed.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow instructs submitting draft JSON-LD to third-party validators without a privacy warning.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The skill explicitly directs submission of JSON-LD to external validators without checking whether the draft contains confidential or unpublished information. In this pre-publication workflow, structured data could disclose embargoed product details, pricing, internal URLs, or personal information; the risk is lower when the submitted data is already public.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 174)May include surrounding context.

md
- Any featured listicle/comparison tool lacks a link.
- Any featured listicle/comparison tool lacks a required image/screenshot.
- Schema contradicts visible content.
- Existing ranking page title/meta/slug was changed without approval/risk note.
- Regulated claims are unsupported.

## Pass threshold