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
E2E自动化工程师 端到端流程测试
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent E2E testing skill that runs repository-supported browser validation and does not show hidden persistence, exfiltration, or destructive behavior.
Install this only in repositories where the Weline E2E command and referenced project docs exist. Expect it to run browser tests and possibly use provided login or seed data for validation; review test credentials and runtime setup before use.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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
Findings (7)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The trigger conditions are broad enough to match generic testing terminology such as 'UI interaction' or 'acceptance path' without clear exclusion rules. In an agent-routing system, this can cause the E2E skill to activate unnecessarily, leading to overbroad browser execution, unintended test runs, or misuse of higher-privilege automation paths on tasks that did not actually require end-to-end validation.
- Content
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/testing/SKILL.md` - `dev/ai/skills/sse-streaming/SKILL.md` - `dev/ai/skills/weline-routing/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/testing/SKILL.md` - `dev/ai/skills/sse-streaming/SKILL.md` - `dev/ai/skills/weline-routing/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/testing/SKILL.md` - `dev/ai/skills/sse-streaming/SKILL.md` - `dev/ai/skills/weline-routing/SKILL.md` # Responsibilities
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The skill name is Chinese while the operational instructions are primarily in English, and the collaboration contract references a Chinese-named shared standard. This introduces an implicit language expectation without stating whether users may choose their preferred language or whether the locale is required for organizational reasons.
- 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.