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 executable payload, but its auto-activation terms are overly broad and may trigger in unrelated conversations.

This skill is reasonable to install for SkillScan-style workflow help, but its implicit invocation and generic keywords could make it appear during unrelated security or productivity tasks. Users who want tighter control should invoke it explicitly or narrow/disable implicit activation.

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: 98% confidence
Finding: The description contains very broad activation terms such as 'work-productivity,' 'security,' and generic requests for workflows, artifacts, or analysis. This can cause the skill to activate for many unrelated prompts, leading to misrouting, unintended instruction injection into conversations, and reduced trust in skill selection; the security-related framing makes over-activation more dangerous because users may treat the output as authoritative.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The trigger keywords include highly common terms like 'security,' 'gate,' 'every,' 'must,' 'before,' and 'activate,' which are likely to appear in many unrelated prompts. Ambiguous triggers increase accidental activation risk and can hijack routing away from more appropriate skills, especially in multi-skill environments where broad matching creates systemic reliability and safety issues.
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 includes very broad everyday terms such as "security", "every", "must", "pass", "before", "activate", and "bug fix", which can cause the skill to activate in many unrelated contexts. Overbroad auto-triggering can misroute user requests, override more appropriate skills, and create prompt-selection ambiguity that weakens reliability and safety controls.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad, generic, and include common security and workflow terms such as 'security', 'gate', 'every', and 'bug fix'. This raises the chance the skill activates in unrelated contexts, which can cause unintended instruction injection into conversations or tool flows and may steer users into the wrong workflow without explicit intent.
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 utterances are broad enough to cause unintended activation for generic requests containing terms like "security," "gate," "every," or "bug fix." In an agent skill-routing context, this can misroute user tasks into the skill unexpectedly, causing incorrect workflow execution, prompt-scope expansion, or interference with safer or more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger section provides examples and keywords but no clear boundaries for when the skill should not activate. Without exclusion rules or specificity thresholds, the skill may match loosely related requests and produce irrelevant or conflicting guidance; in a security-oriented skill, that can mislead users into relying on the wrong workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: 该文件整体为 SKILL.zh-CN.md 中文版本，内容中未说明这是可选语言，也未给出用户可选择其他语言的提示。按规则，若技能隐含强制特定语言而没有用户选择或合理限定，属于自然语言/地区策略问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description says the skill should be used when a user asks for broad categories like work-productivity, skillscan, security, or practical workflow support, but it does not define precise boundaries for when this skill is preferred over others. This ambiguity increases the chance of accidental invocation and inconsistent routing, especially in multi-skill environments where several skills may plausibly match the same request.
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 highly generic and includes broad terms tied to common workplace requests, which can cause the skill to activate in situations the user did not explicitly intend. In combination with a security/workflow helper theme, this increases the chance of unsolicited prompt injection into unrelated conversations and can steer agent behavior beyond clear user consent.
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 boundaries allows the platform to auto-select this skill for loosely related requests, creating unnecessary exposure to overreach and misactivation. Because this skill is framed around security, bug fixing, hardening, and workflow assistance, accidental invocation could influence sensitive tasks or inject workflow instructions where they are not appropriate.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are overly broad and include common words and phrases such as 'security', 'gate', 'every', 'must', and 'pass, before, activate, bug fix', which can cause the skill to activate in many unrelated contexts. In an agent ecosystem, broad activation increases the chance of unintended invocation, prompt-routing collisions, and misuse of this skill in situations the user did not intend, which can lead to incorrect workflow execution or security-review bypass by misclassification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The README labels SKILL.md as "English skill instructions" while also listing a Chinese variant, but it does not state that users may choose their preferred language or that language selection is optional. This can be read as a default language constraint without explicit opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: Although this is labeled as a Chinese README, core user-facing content such as the demand description, workflow description, keywords, and trigger phrases remains in English. This can amount to an implicit language policy constraint or inconsistency without user opt-in or explanation.
Content: No source excerpt is available for this finding.