Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style workflow skill with overly broad auto-activation cues, but no hidden code, data collection, destructive behavior, or persistence.

Installers should be aware that this skill may auto-activate too broadly because implicit invocation is enabled and the trigger words are generic. It is suitable as a workflow/checklist helper, but maintainers should narrow the triggers or require explicit invocation for cleaner routing.

A.I.G

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

SkillSpector

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad enough to match common requests like 'security', 'every', 'must', 'before', or 'bug fix', which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user tasks into this workflow, creating prompt hijacking opportunities, incorrect tool selection, or unsafe automation in contexts the skill was not designed for.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is scoped so broadly that it can match many ordinary requests unrelated to a specific security workflow. This increases the chance of unintended activation, causing the agent to apply this skill in the wrong context and potentially override more appropriate safety, routing, or task-specific behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include extremely generic terms like 'security', 'gate', 'every', 'must', 'pass', and 'before', which are likely to appear in many benign prompts. Such broad triggers can cause accidental invocation and misrouting, making the skill act on requests it was never intended to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: 触发关键词包含 security、every、must、pass、before、activate 等高频通用词，容易在大量无关对话中误触发该技能。误触发会扩大技能介入面，在安全相关场景下可能造成错误路由、越权式上下文注入或让用户在未明确请求时收到不恰当的操作建议。
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are extremely broad and include common words like "security," "gate," and "every," which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance that this skill intercepts requests outside its intended scope, leading to workflow hijacking, user confusion, or accidental application of security-oriented guidance where it does not belong.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords and example phrases are broad enough to match many ordinary security or productivity requests, which can cause this skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user inputs into this workflow, increasing the chance of inappropriate guidance, prompt interference, or unintended privilege/use of the skill in contexts where it was not requested.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The file is labeled as a Chinese README, but substantial user-facing content including the title, core description, and trigger phrases is presented in English. This imposes a language choice on users without opt-in or explanation, which can violate language/locale policy expectations for user-facing skill materials.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger sentences are vague, repetitive, and do not define realistic boundaries for when the skill should or should not activate. Poor trigger examples reinforce overbroad matching behavior and make it harder for integrators to implement safe routing, increasing the likelihood of accidental invocation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: 技能描述将适用范围定义为 work-productivity, skillscan, security, gate, every 或任何需要流程、清单、分析、实现支持的请求，边界非常宽泛。这样的定义会让调度器难以区分该技能与其他通用技能，增加错误激活和在不适合的上下文中输出安全/实现建议的风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt contains very broad, generic activation language such as 'help me' and wide topical terms, which can overlap with many ordinary user requests. In combination with implicit invocation, this increases the chance the skill is auto-selected outside narrowly intended contexts, causing unintended prompt injection surface expansion or unwanted workflow execution.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Enabling implicit invocation without tight constraints allows the platform to auto-activate this skill based on loose relevance matching rather than explicit user intent. Because the skill is framed as a broad workflow helper, this can cause unintended invocation in unrelated conversations, exposing users to hidden instructions or expanding the effect of any unsafe behavior embedded in the skill.
Content: No source excerpt is available for this finding.