Back to skill

Security audit

tiktok-slideshow-agent

Security checks for vulnerabilities and agentic risk

Overview

The preview uploads photos and slide text despite saying nothing is sent, creating a privacy concern that warrants review.

Treat --dry as an online preview: it uploads photos and slide text while skipping the posting request. Use only content you approve for PostWire processing, and have the preview wording corrected before relying on it. Keep draft mode unless you intend immediate publication, check additional network targets, and explicitly scope recurring reviews. Both bundled files were inspected; hosted retention and account-permission enforcement remain unverified.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

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

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 dry-run instruction says it “sends nothing” without warning that slide rendering transmits content to PostWire.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

Describing the preview command as sending nothing can lead users or agents to submit private photos and slide text under the mistaken belief that processing stays local. The documented server-side rendering workflow indicates that previews transmit content to PostWire; earlier disclosure of server-side rendering mitigates, but does not resolve, this misleading assurance. The implementation is not provided, so the assessment rests on the documented workflow rather than verified script behavior.

Content

No source excerpt is available for this finding.