ClawHub
Back to skill

Security audit

ad-campaign

Security checks for vulnerabilities and agentic risk

Overview

The skill creates advertising artwork through Canvora using disclosed inputs and credits, with no evidence of hidden or unrelated actions.

Share only campaign material you are authorized to send to Canvora, agree on a credit budget, and verify the separately installed CLI and setup skill.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The generation workflow sends campaign inputs to Canvora without a privacy disclosure.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The canonical workflow instructs the agent to submit product URLs, written briefs, and brand inputs to Canvora for generation. Although the skill discloses credit costs, it does not warn users that these potentially confidential campaign inputs are transmitted to a third-party service.

Content

No source excerpt is available for this finding.