Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad auto-activation wording but no evidence of hidden execution, data access, persistence, or exfiltration.

Installers should be aware that this skill may activate on overly broad security or workflow-related requests. It is safest to invoke it explicitly by name and narrow the trigger policy before broad deployment, but the inspected package itself does not show hidden or dangerous behavior.

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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad enough to match ordinary user requests such as generic work-productivity, security, bug-fix, or workflow queries, which can cause this skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can silently route unrelated tasks through this skill, increasing the chance of prompt hijacking, unintended behavior, or policy bypass via skill invocation confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says to use the skill whenever a user asks for broad topics like 'work-productivity', 'security', or 'analysis', without defining scope limits or disambiguation rules. That ambiguity can over-route unrelated requests into this skill, leading to confused behavior, degraded trust, and possible bypass of more appropriate skills or safeguards.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list is extremely broad and includes generic terms like 'security', 'gate', 'every', 'must', and 'before', which can match many unrelated prompts. This can cause unintended activation of the skill in contexts the user did not intend, increasing the chance of prompt-routing errors, irrelevant instructions, or unsafe workflow interference.
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 common terms such as "security", "every", "must", "pass", and "before", which can cause the skill to activate in many unrelated conversations. Over-broad activation in a security-oriented workflow helper can misroute user requests, inject irrelevant instructions into other tasks, and increase the chance of unsafe or confusing agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger examples and keyword list include generic terms such as "security," "gate," "every," and "must/pass/before/activate," which are common in unrelated requests. This can cause the skill to activate outside its intended scope, unexpectedly inserting workflow guidance into unrelated conversations and potentially interfering with higher-priority security or operational tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are extremely broad and include generic terms like "security," "gate," "every," and "bug fix," which can cause the skill to activate in many unrelated contexts. In an agent ecosystem, overbroad activation boundaries can route sensitive or unintended tasks into this skill, increasing the risk of misexecution, prompt hijacking through incidental invocation, or user confusion about which workflow is acting.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This file is presented as a Simplified Chinese README, but prominent user-facing content such as the title and requirement description is written in English. That creates a language/locale consistency issue and effectively forces English for part of the experience without any opt-in or explanation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger examples are malformed, incomplete, and still rely on broad phrasing, so they fail to communicate reliable activation constraints. Poor examples can train routing or human operators to invoke the skill on weak matches, increasing accidental activation and inconsistent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill description says it should be used when users ask for broad categories like work-productivity, skillscan, security, gate, or every, or when they need practical workflow or analysis support, but it does not clearly define scope limits. This ambiguity makes unintended activation more likely, especially because some listed terms are generic and the skill is framed as broadly applicable across bug fixing, hardening, reliability, and adjacent skill creation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt embeds a very broad activation phrase using common terms like 'help me' and generic work/security language, which can cause the skill to be selected during ordinary user requests that were not intended for this specific capability. In combination with the vague, keyword-heavy description, this increases the chance of accidental invocation, prompt hijacking of unrelated tasks, and unexpected exposure of the skill's instructions or behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without clear trigger constraints allows the platform to auto-select this skill based on loose semantic matches rather than explicit user intent. Because this skill is described with broad productivity and security terms, it may activate in unrelated contexts, leading to unintended tool use, confusion, or unsafe routing of sensitive requests through the wrong skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger scope is loosely defined through broad keywords and templated trigger sentences rather than precise eligibility rules. Ambiguous activation boundaries increase the chance of accidental invocation, causing context confusion, tool misrouting, and possible suppression or dilution of the user's actual intent when other skills would be more appropriate.
Content: No source excerpt is available for this finding.