Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-style workflow helper with no executable code or data access, though its automatic activation wording is too broad.

Install only if you want a broad SkillScan-style workflow helper. Because implicit invocation is enabled and the trigger terms are generic, review or narrow the activation rules so it does not appear during unrelated security, bug-fix, or workflow requests.

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 (14)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description is broad enough to match many ordinary requests because it includes generic domains and action words like "security," "workflow," "analysis," and "implementation support" without clear scope boundaries. This can cause unintended invocation, exposing users to the wrong skill behavior, confusing routing, and increasing the chance that sensitive or unrelated tasks are handled by an ill-fitting skill.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The keyword list contains everyday terms like "security," "gate," "every," "must," "pass," and "before," which are likely to appear in many unrelated prompts. Overbroad triggers materially raise the risk of accidental activation, prompt-routing interference, and inappropriate disclosure or task execution under the wrong skill context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description says to use the skill when a user asks for broad categories like work-productivity, security, or practical workflow support, which is ambiguous and covers many unrelated requests. This can lead to over-invocation and misapplication of the skill, creating opportunities for unintended behavior and reducing the reliability of skill selection.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes very generic terms such as "security", "every", "must", "pass", and "before", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance of incorrect routing, prompt-surface expansion, and accidental execution of workflows in contexts the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger guidance includes extremely broad everyday terms such as "every" and generic security/workflow language that can match many unrelated user requests, causing unintended activation of the skill. In an agent-routing context, overbroad triggers can silently invoke this skill outside its intended scope, leading to workflow hijacking, confusing behavior, or unsafe substitution of security guidance where it was not requested.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The keyword list is broad and ambiguous, using common words like 'security,' 'gate,' 'every,' 'must,' and 'before,' which are likely to appear in unrelated requests. In an agent ecosystem, this increases accidental invocation and misrouting risk, which is more concerning because the skill is positioned as a security workflow helper and may influence analysis or decision-making in contexts where it was not intended.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger guidance includes extremely generic language such as 'Help me' and 'I need a practical workflow,' which overlaps heavily with normal user conversation. This can cause unintended skill activation or routing, especially in systems that use heuristic or keyword-based dispatch, leading to the wrong skill handling sensitive security-related requests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This Chinese README contains substantial English instruction text and trigger phrases, but does not state whether users may choose their preferred language or locale. That can amount to a language-policy issue because the skill appears to impose mixed/English phrasing without clear opt-in or justification.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger guidance uses broad everyday terms such as security, gate, every, must, pass, before, and activate, which can cause the skill to activate in many unrelated conversations. In an agent environment, overbroad activation can route sensitive or off-topic requests into this workflow unexpectedly, increasing the chance of incorrect handling, prompt-scope confusion, or unintended influence over security-related tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger sentences use vague phrasing and effectively demonstrate invocation on generic requests rather than clearly bounded scenarios. This reinforces ambiguous activation behavior and makes it more likely that the skill will be invoked for loosely related or unrelated user inputs.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The file is explicitly a zh-CN localized skill document, but the content does not state that language selection is optional or user-driven. Under the policy, forcing a specific language or locale without opt-in can be a natural-language policy violation unless the locale restriction is clearly justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt includes very broad, everyday trigger terms like 'work-productivity', 'security', 'workflow', and 'help me', which can cause the skill to activate for unrelated user requests. This increases the chance of accidental routing, context hijacking, or invocation in situations where the user did not intend to use this skill, especially because the skill is framed as broadly applicable implementation support.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Enabling implicit invocation without tight activation constraints allows the platform to call this skill automatically based on loose matches. Combined with the broad prompt wording, this makes unintended invocation significantly more likely and can expose users to incorrect workflow injection, confusion, or unreviewed behavior in unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation section lacks precise activation boundaries and provides natural-language trigger sentences that are themselves broad enough to match common requests about help, workflows, bugs, or hardening. This increases the chance that an orchestrator or agent selects the skill opportunistically, which is especially risky for a security-related helper because it may override more appropriate tools or analyses in unrelated contexts.
Content: No source excerpt is available for this finding.