T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:8- Finding
Over-Privileged Bearer Credential Embedded in MCP Connector URL
- Content
View full analysis
- Remediation
View remediation
Security audit
Tiktok Publisher
Security checks for vulnerabilities and agentic risk
Overview
This skill is a real TikTok publishing connector, but it uses a bearer-token MCP URL with public-posting authority and describes its data flow inconsistently.
Install only if you are comfortable giving the Boring MCP connector posting authority. Treat the connector URL like a password, prefer draft mode when possible, confirm which accounts are connected, and revoke or regenerate the token if the URL is exposed.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
Findings (1)
Vulnerability Patterns
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 70% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
md - **Video limits**: Max 4GB, max 10 minutes - **Photo carousel**: Up to 35 images (PNG auto-converts to JPEG) - **Draft mode**: Sends to creator's inbox for manual publish - **Token**: 24-hour access token with auto-refresh (refresh token lasts 1 year) - **Permissions**: `video.upload`, `video.publish` ## Error Handling
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 99% confidence
- Finding
The skill’s Security & Data Handling section makes a misleading claim that analytics queries are read-only and that no content is uploaded or modified, while the rest of the skill explicitly instructs users to upload media and publish or draft TikTok posts. This contradiction can cause users to underestimate the sensitivity of the connector token and the real write capabilities of the service, increasing the risk of unsafe credential handling and unintended posting.
- Content