Back to skill

Security audit

TalkToAds: Meta Ads for AI Agents

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because a scanner found that it automatically saves brand preferences without a privacy notice; the review is incomplete because one reference could not be resolved.

Review the skill’s data-saving behavior before installing, especially what preferences it stores and what controls are available. The scan covered the listed components but was marked partial because a local path-like reference 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
  • 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)

Brand preferences are automatically persisted without a user-facing privacy notice.

Medium
Category
Output Handling
Confidence
85% confidence
Finding

The skill directs the agent to persist lasting preferences using remember_brand_fact without first explaining the storage destination, retention, or user controls, or distinguishing an explicit request to remember from an ordinary statement. In this advertising context, preferences can include commercially sensitive target CPA values and effective audiences, so automatic persistence through the remote service creates a privacy and confidentiality risk, although no malicious collection or unauthorized access is demonstrated.

Content

No source excerpt is available for this finding.