Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper, but its broad trigger words may make it run in unrelated conversations.

Install only if you want a broad workflow helper for skill-vetting and reliability tasks. Be aware it may activate on common words like security, before, github, or bug fix; explicit invocation by skill name would be safer than relying on automatic 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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list is overly broad and includes common terms such as 'security', 'first', 'before', and 'github', which can cause the skill to activate in many unrelated conversations. This creates prompt-scope confusion and increases the chance that the skill injects workflow instructions or security framing where the user did not intend to invoke it, degrading agent reliability and potentially steering sensitive tasks incorrectly.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger list is overly broad and includes common terms such as 'security', 'first', 'before', 'github', and 'bug fix', which can cause the skill to activate in many unrelated conversations. This creates a prompt-scope hijacking risk where the assistant may inappropriately route benign user requests into this skill, leading to incorrect behavior, unintended disclosure of context to the skill, or interference with more appropriate safety or task-routing logic.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad, generic, and overlap with common user language such as 'help me', 'practical workflow', 'security', and 'github', which can cause the skill to activate in contexts far outside its intended scope. In a security/vetting-related skill, this increases the chance of accidental invocation, confusing routing, and unintended handling of requests that may involve sensitive or higher-risk tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation section does not define clear boundaries for when the skill should or should not run, and it mixes broad keywords like 'security', 'first', 'before', and 'github' with generic trigger sentences. This increases the chance of accidental invocation during unrelated conversations, especially because the skill concerns vetting and security-adjacent workflows where misrouting can affect decision-making and trust.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger examples include broad natural-language phrases such as 'Help me' and 'I need a practical workflow' around generic security/workflow tasks, which can cause the skill to activate in unintended contexts. In an agent ecosystem, overbroad activation can route unrelated user requests into this skill, leading to mistaken guidance, unnecessary handling of sensitive security topics, or workflow confusion.
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 and include generic security/workflow terms such as 'security', 'first', 'before', 'github', and 'bug fix', which can cause the skill to activate in unrelated conversations. Unintended invocation can route user requests into the wrong workflow, increasing the chance of irrelevant guidance, prompt hijacking exposure, or misuse in contexts where the skill was not intended to run.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description says to use the skill when a user asks for broad categories like 'work-productivity' or 'security' or 'needs a practical workflow,' which are ambiguous and likely to match many benign requests. Ambiguous activation criteria can cause accidental routing to this skill, leading to unintended instruction injection and reducing trust in skill selection behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The example trigger phrases are malformed, truncated, and not clearly tied to a precise invocation pattern, so they fail to constrain when the skill should run. Poor examples make implementers more likely to rely on fuzzy matching, which compounds accidental activation risk and misroutes user requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The activation description says to use the skill when a user mentions broad categories like work-productivity, security, or needs practical workflow or analysis support, which is vague enough to match a very wide range of unrelated tasks. Ambiguous routing conditions increase the chance of accidental invocation, causing overreach into conversations outside the skill's intended domain and degrading both safety and reliability.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The default prompt is overly broad and loosely phrased, which can cause the skill to be invoked in contexts only tangentially related to the intended task. Combined with implicit invocation, this increases the chance of unintended activation and accidental exposure of users to security-analysis or workflow guidance they did not explicitly request.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This is a Chinese README, but key descriptive content is written in English and presented as the default text rather than as an optional language choice. The file does not indicate that users may select their preferred language or that the mixed-language presentation is intentional and justified.
Content: No source excerpt is available for this finding.