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
QA测试主管 质量门禁验收
Security checks for vulnerabilities and agentic risk
Overview
This is a QA review skill that asks the agent to evaluate test evidence and release readiness, with no hidden execution, persistence, credential use, or destructive behavior found.
Installers should expect this skill to read project QA evidence, related Weline process documents, and named project skill files when available. It is suitable for teams using that Weline workflow; users outside that environment may need to adapt the referenced documents and Chinese role names.
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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- 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
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/testing/SKILL.md` - `dev/ai/skills/planning/SKILL.md` - `dev/ai/skills/documentation-standards/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/planning/SKILL.md` - `dev/ai/skills/documentation-standards/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/planning/SKILL.md` - `dev/ai/skills/documentation-standards/SKILL.md` # Responsibilities
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The file is primarily written in English, but L78 requires following a shared skill named in Chinese, indicating a language-specific dependency. The skill does not state that users may choose their preferred language or explain why this locale constraint is necessary, which can violate language/locale policy requirements.
- 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.