Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no code execution or persistence, though its activation wording is overly broad.

Install only if you want a general SkillScan-style workflow helper. Be aware that its current trigger wording is broad, so it may be selected for loosely related security or bug-fix prompts unless the platform or user narrows invocation.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are extremely broad and include generic terms such as 'security', 'gate', 'every', 'must', and 'before', which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation increases the chance the skill is invoked on unrelated or sensitive tasks, potentially causing unsafe workflow injection, incorrect delegation, or unintended influence over security-relevant decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation description is so broad that it effectively claims a wide class of work-productivity, security, checklist, analysis, and implementation requests. In a multi-skill environment, this creates unsafe ambiguity, allowing the skill to activate outside its intended domain and potentially influence outputs where more specialized or safer skills should handle the request.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list is excessively broad and includes common terms like "security," "every," "must," and "before," which are likely to appear in ordinary user requests unrelated to this skill. This can cause unintended activation, hijack routing from more appropriate skills, and increase the chance that an agent applies the wrong workflow in security-sensitive contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description says to use the skill whenever users ask for broad categories like work-productivity, skillscan, security, or practical workflows, but it does not define clear boundaries for when the skill should or should not apply. This ambiguity increases the chance of overbroad activation, misrouting, and unintended influence over tasks outside the intended domain.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger list includes very generic words such as "security", "every", "must", "pass", and "before", which are common in ordinary user prompts. This can cause the skill to activate unintentionally in unrelated contexts, leading to prompt/skill routing errors and potentially inserting irrelevant workflow guidance into sensitive tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger examples are broad enough to match ordinary user phrasing rather than a clearly intentional request for this specific skill. That can cause unintended activation, routing the user into a security workflow they did not ask for and potentially exposing unrelated inputs or causing confusing autonomous behavior in multi-skill environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases and keywords are broad enough that the skill may activate on incidental mentions of generic terms like "security," "workflow," "gate," or "bug fix," rather than on an explicit user request for this specific skill. In an agent ecosystem, unintended invocation can cause the wrong workflow to run, leading to incorrect guidance, task hijacking, or unsafe automation being applied in the wrong context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 78% confidence
Finding: This Chinese-language README presents key usage content and trigger phrases in English, but does not state that users can choose their preferred language or locale. That can amount to forcing a specific language experience without clear opt-in, which conflicts with the language/locale policy requirement.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example trigger phrases encourage invocation from generic natural-language requests without demonstrating any strict qualification criteria. This reinforces overbroad matching behavior and makes accidental activation more likely, especially when users ask for general help with fixing bugs or hardening systems.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The file is written as a Chinese-localized skill document ("SKILL.zh-CN.md") and presents instructions entirely in Simplified Chinese without stating that language choice is optional. This can indicate a locale constraint without explicit user opt-in or justification within the document.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt is overly broad and uses generic terms like 'help me' and broad topical language, which increases the chance the platform may invoke this skill for loosely related user requests. In a security-oriented workflow helper, unintended activation can expose users to irrelevant or risky automation paths, reduce user control, and create prompt-routing confusion that an attacker could potentially exploit through crafted phrasing.
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 strong trigger constraints allows the skill to be auto-selected based on weak semantic matches rather than explicit user intent. Because this skill is framed around security workflows and implementation support, accidental invocation could cause inappropriate handling of sensitive requests, overbroad assistance, or routing into a privileged-seeming security context the user did not actually request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: Even with more context, the trigger sentence still resembles natural language a user might say in many unrelated troubleshooting or hardening scenarios. In an agent platform that auto-selects skills from trigger text, this increases false-positive invocation risk and can lead to mis-executed workflows, incorrect tool use, or accidental processing of sensitive project context.
Content: No source excerpt is available for this finding.