Back to skill

Security audit

Rankizz SEO Skills

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its prompt research flow may send user-supplied prompts to external AI services without a privacy warning; the scan also has one unresolved reference.

Before installing, consider whether prompts you might use contain confidential, personal, or unpublished information. Check which external AI providers would receive them and whether you are comfortable with that disclosure. The scan inspected all three listed components, but completeness is marked partial because a referenced local path could not be resolved, so the evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 23)May include surrounding context.

md
3. Reuse valid context. Do not reinstall a skill or recreate project files that are already current.
4. Ask only for missing information that would change the workflow.

Never ask the user to paste an API key, OAuth token, password, or other secret into chat or a project file.

## Select the smallest useful skill set

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

sh
mkdir -p .agents/skills/rankizz-audit-site-local
curl -L https://www.rankizz.com/skills/rankizz-audit-site-local.zip -o rankizz-audit-site-local.zip
unzip -q rankizz-audit-site-local.zip -d .agents/skills/rankizz-audit-site-local

AI prompt research sends the supplied prompt to external services without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs the agent to submit a supplied prompt through Rankizz to selected external AI providers without checking for sensitive content or establishing whether the user authorized that disclosure. External research is consistent with the skill's purpose, but prompts containing confidential client information, personal data, or unpublished strategy could cross organizational boundaries without the user's informed awareness.

Content

No source excerpt is available for this finding.