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
CI发布工程师 环境兼容与命令安全
Security checks for vulnerabilities and agentic risk
Overview
This skill mainly gives guidance for safer automation commands and does not include hidden code or persistence.
Install this only if you are comfortable with a Weline-oriented CI command-safety skill that may inspect and validate specific automation commands you provide. Keep any command runs focused and review them before execution, especially in release or CI environments.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
Findings (6)
Skill Enumeration
Medium
- Category
- Agent Snooping
- Confidence
- 80% confidence
- Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Content
md - `AI-ENTRY.md` - `CLAUDE.md` - `dev/ai/skills/windows-command-quoting/SKILL.md` - `dev/ai/skills/php84-performance/SKILL.md` - `dev/ai/skills/create-framework-command/SKILL.md`
Skill Enumeration
Medium
- Category
- Agent Snooping
- Confidence
- 80% confidence
- Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Content
md - `AI-ENTRY.md` - `CLAUDE.md` - `dev/ai/skills/windows-command-quoting/SKILL.md` - `dev/ai/skills/php84-performance/SKILL.md` - `dev/ai/skills/create-framework-command/SKILL.md` # Responsibilities
Skill Enumeration
Medium
- Category
- Agent Snooping
- Confidence
- 80% confidence
- Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- Content
md - `CLAUDE.md` - `dev/ai/skills/windows-command-quoting/SKILL.md` - `dev/ai/skills/php84-performance/SKILL.md` - `dev/ai/skills/create-framework-command/SKILL.md` # Responsibilities
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The collaboration contract requires following a shared skill named in Chinese (
通用工程师-开发规范与代码质量), while the rest of the skill description is primarily in English and does not offer any language choice. This creates a natural-language policy concern because it can effectively force a specific language context on users or agents without explicit opt-in or justification.- Content
Scope Creep
Low
- Category
- Excessive Agency
- Confidence
- 75% confidence
- Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
- Content
md - Know the Weline AI agent roster defined in the shared skill and `dev/ai/agent/README.md`. - Keep work inside this specialist's ownership boundary. - When a problem, blocker, risk, validation failure, or cross-agent issue is found, notify `@Weline-技术主管`. - Do not silently expand scope to fix another agent's area. - Include collaboration status in the final report.