Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. Read `SKILL.md` frontmatter first and judge whether the trigger description is specific enough.
Security audit
Work Productivity Skill Vetter Workflow Helper
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only skill for reviewing other skills, with some broad trigger wording but no hidden code, persistence, credential access, or destructive behavior.
Install only if you want a workflow helper for reviewing other skills. Be aware that some non-primary files use broad trigger language and implicit invocation is enabled, so it may be selected in loosely related skill/security discussions; tightening those triggers would improve predictability.
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 (10)
Vague Triggers
High
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The trigger keywords include very broad, high-frequency terms such as “security”, “first”, “before”, and “github”, which can cause the skill to activate in many unrelated conversations. Over-broad auto-triggering can unexpectedly insert this skill’s workflow into security- or installation-related tasks, creating prompt-scope interference and reducing user control over which skill is invoked.
- Content
Vague Triggers
High
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The trigger sentences are highly generic and partially malformed, matching broad phrases like 'Help me' and 'I need a practical workflow' around common productivity and security terms. This can cause unintended skill activation in unrelated conversations, leading the agent to apply the wrong workflow or expose users to inappropriate guidance during sensitive vetting tasks.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger sentences are broad, repetitive, and not clearly bounded to a narrow user intent, which increases the chance the skill will activate in unrelated contexts. For a skill that influences safety and installation decisions, accidental invocation can cause noisy or inappropriate vetting behavior, reduce trust, and interfere with other workflows.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger phrases are broad, awkwardly phrased, and likely to match loosely related requests, which can cause the skill to activate when the user did not explicitly ask for it. In a skill that influences vetting, installation, or security-related workflow decisions, accidental invocation can misroute user tasks and surface unintended guidance at sensitive decision points.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
文件名和正文整体采用
zh-CN中文区域版本，但文中未说明这是可选语言版本，也未向用户提供语言/locale 选择。按规则，若技能强制特定语言或区域设置而没有用户选择或合理说明，属于自然语言策略问题。- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The description says to use the skill when the user mentions broad concepts like work-productivity, security, or first, or when they need surrounding support, which leaves the activation boundary vague. This increases the chance of accidental invocation on unrelated tasks, especially because the skill’s domain overlaps with common security and productivity discussions.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The default prompt is broad and generic enough that it could be invoked for many ordinary requests about reviewing or deciding on skills, without explicit limits on when the skill should apply. In a skill that itself performs safety and publication vetting, over-broad activation can cause unintended routing, analysis of the wrong content, or overreliance on this helper in contexts where narrower review criteria should be used.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
Enabling implicit invocation without documented boundaries allows the platform to auto-select this skill in loosely related conversations, increasing the chance of unintended activation. Because this skill influences install/keep/publish decisions for other skills, accidental invocation can affect trust and safety review workflows and may cause inappropriate recommendations to be treated as authoritative.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 71% confidence
- Finding
This is a Chinese README, but the key operational text in '这个技能如何满足需求' and all listed trigger phrases are presented in English. That can amount to a language/locale policy concern because the skill appears to require or privilege English usage without explicitly offering a language choice or documenting the constraint.
- Content