Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
L06 将触发描述写成“被限流了”“超时”“调用不稳定”等宽泛问题陈述，并混合了场景描述与触发词列表，缺少明确边界，容易与一般性技术讨论重叠。文中也未提供不应触发的反例或更严格的上下文约束，因此存在歧义触发风险。
- Content
Security audit
api-resilience
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small API resilience guide and demo script with no evident network access, persistence, credential handling, or destructive behavior.
Install if you want Chinese/English guidance and a simple demo for retry/backoff/circuit-breaker patterns. Be aware the trigger wording is broad, so agents may load it for general timeout or reliability questions; users should still review real production changes involving live APIs, credentials, writes, deployment, or publishing.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The description says the skill should be used when the user says phrases like '怎么给agent加重试退避' and also for general conditions such as third-party services being unstable. This mixes specific examples with broad activation conditions and does not provide negative examples or clear limits on when similar reliability questions should not invoke the skill.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
Items like '一次失败就让整条链路崩' and '用户问「怎么让外部调用更稳」' are broad enough to overlap with many general debugging or optimization situations. The file does not clarify whether the skill is limited to external third-party dependency resilience versus any unstable call path.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This code includes a Chinese-only module description and multiple Chinese-only user-facing messages. The file provides no option for the user to select a language or locale, which is a natural-language policy concern under the language/locale rule.
- Content