Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is not clearly malicious, but it should be reviewed because it can auto-activate on very common words and steer unrelated requests.

Review before installing. The main concern is not hidden code, but broad automatic activation: narrow the trigger keywords to skill-vetting-specific phrases and disable or tightly constrain implicit invocation before using it in security, GitHub, or bug-fix workflows.

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: 97% confidence
Finding: The trigger phrases are broad enough to match common, everyday requests such as generic security, GitHub, or bug-fix help, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the chance of unintended routing, confusing user intent, and over-applying a workflow to unrelated tasks, especially because the skill presents itself as generally applicable to practical workflows and security-related requests.
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 when a user asks for broad categories like 'work-productivity', 'security', or 'implementation support' without defining clear boundaries. Ambiguous invocation criteria increase the chance that the skill activates outside its intended use case, which is especially risky for a security-adjacent helper because users may receive misplaced trust signals or mismatched workflow guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords include very broad terms such as 'security', 'first', 'before', and 'github', which are common in many unrelated conversations. This can cause accidental invocation of the skill in contexts the user did not intend, leading to scope confusion, irrelevant guidance, or inappropriate handling of sensitive security-related requests.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords are overly broad and include common terms such as "security", "first", "before", and "github", which can cause the skill to activate in many unrelated conversations. This creates an unsafe routing condition where a user may be steered into this skill unexpectedly, increasing the chance of irrelevant guidance, prompt-scope confusion, or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt contains a very broad invocation phrase tied to common terms like work-productivity, security, analysis, checklist, and implementation support. In combination with the skill’s broad description, this can cause the agent to activate in unrelated conversations, creating prompt injection surface and potentially routing sensitive or security-relevant user requests into this skill unexpectedly.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Enabling implicit invocation without tight trigger constraints allows the platform to auto-select this skill based on loosely matching everyday language. Because this skill is framed around security, bug fixing, hardening, and implementation help, accidental invocation could expose user context to an unnecessary skill path or let the skill influence sensitive workflows without explicit consent.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are broad enough to match common requests containing words like 'security', 'first', 'github', or generic phrases such as 'I need a practical workflow', which can cause the skill to activate outside its intended scope. In an agent environment, overbroad routing can divert unrelated user tasks into this workflow, leading to inappropriate handling of security-sensitive requests and reducing trust in skill-selection boundaries.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger phrases are broad, generic, and include common terms like 'security', 'first', 'before', and 'github', which can cause the skill to activate in unrelated contexts. In an agent ecosystem, overbroad activation can route sensitive or off-topic user requests into this workflow unexpectedly, increasing the chance of incorrect handling, prompt interference, or unintended disclosure of context to a skill that was not explicitly intended.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: Although this is labeled as a Chinese README, substantial user-facing content and trigger phrases are written in English, including the title, requirement text, usage description, and activation examples. This can effectively impose a language preference without user opt-in and may violate language/locale expectations for localized skill documentation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger section provides only positive examples and no exclusion rules, so the system lacks safeguards against accidental or overly broad activation. Without negative examples, generic language in user prompts may match this skill even when the user is not asking for skill-vetting help, increasing misrouting and unintended influence over responses.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description says to use the skill when users ask for broad categories like work-productivity, security, or practical support, but it does not clearly define when the skill should not trigger. Ambiguous activation guidance can cause accidental invocation in unrelated security or productivity contexts, reducing reliability and potentially misdirecting user requests.
Content: No source excerpt is available for this finding.