Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Github Auto
Security checks for vulnerabilities and agentic risk
Overview
The skill appears to be a GitHub automation helper, but its token use and broad repository actions are not scoped clearly enough for automatic trust.
Review before installing. Use a least-privilege GitHub token, preferably limited to specific repositories, and require explicit confirmation before any action that merges code, changes Issues or PRs, triggers workflows, deletes branches, or publishes releases. Treat the 'no API key' metadata claim as inaccurate because the skill says it needs GITHUB_TOKEN.
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
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The manifest advertises broad automation over PRs, Issues, CI/CD, and releases but does not disclose operational boundaries, approval requirements, or potentially destructive repository actions. In a GitHub-management skill, this omission is risky because users may grant broad trust to actions that can merge code, alter workflows, publish releases, or otherwise affect repository integrity.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
The visible skill name and description are written only in Chinese, with no indication that users may choose another language or that the skill is intended for a Chinese-only audience. This can be a natural-language policy concern when a skill appears to impose a locale without opt-in or documented regional justification.
- Content