ClawHub
Back to skill

Security audit

AI Creative Studio

Security checks for vulnerabilities and agentic risk

Overview

This skill creates local marketing drafts with proportionate file access, though its suggested claims and campaign settings need human review.

Use a dedicated output folder because existing generated files can be overwritten. Review every claim before publishing: stock offers and test claims can appear even when the report shows PASS. Before implementing tracking, retargeting, or paid campaigns, review privacy controls and approve the settings and budget separately. Provider keys are unnecessary for the bundled script.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/campaign-playbook.md (reported line 43)May include surrounding context.

md
- Change one variable per test: hook, offer, or creative format - never two.
- Minimum 3 variations per ad set.
- Do not judge a creative before ~1000 impressions or ~20 clicks.
- Kill winners are rare - kill the bottom third, scale the top third.
- Keep a "loss log": what you tested, what it cost, what happened.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The launch workflow enables tracking and behavioral retargeting without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs the agent to launch with tracking enabled and retarget people based on video-viewing behavior. These actions affect visitor privacy, but the playbook does not warn about behavioral data collection or advertising-platform use; the later privacy-policy requirement applies only to email capture.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.