Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-help skill for OpenAPI and Swagger work, with broad trigger wording but no hidden execution, data access, persistence, or destructive behavior.

Install this skill if you want help with OpenAPI or Swagger documentation. Be aware it may be invoked more broadly than ideal for API-related prompts, so explicitly choose or avoid it when working on unrelated backend tasks.

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

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are generic and malformed enough that they could cause the skill to activate in situations broader than intended, especially when users mention common API documentation terms or partial phrasing. In an agent ecosystem, ambiguous invocation boundaries can lead to incorrect tool selection, prompt hijacking opportunities through incidental matching, or unintended disclosure of internal workflow instructions.
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 broad enough to activate on generic OpenAPI, Swagger, REST API, or workflow-related requests, which can cause the skill to run outside its intended scope. In an agent system, overbroad routing can lead to prompt hijacking exposure, accidental execution of the wrong workflow, or leakage of context into an unrelated task.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description is broad enough to trigger on generic terms like software-and-data, openapi, swagger, and API documentation without strong scope boundaries. In agent-routing systems, this can cause the skill to activate for loosely related prompts, creating misrouting and increasing the chance that inappropriate instructions or workflows are injected into unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keyword list contains ambiguous, high-collision terms such as 'software-and-data' and broad API-related phrases that appear in many unrelated engineering requests. This increases unintended invocation risk, which can degrade routing integrity and cause the skill to influence conversations outside its intended domain.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation description is broad and mixes generic software topics with common API terms, which can cause the skill to be invoked outside its intended scope. Over-broad triggering increases the chance of inappropriate routing, causing users to receive mismatched guidance or exposing this skill in contexts where another, more constrained skill should respond.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The example trigger phrases use highly generic lead-ins like "Help me" and "I need," making accidental activation more likely when users ask for unrelated assistance. Because these examples can influence trigger design or matching behavior, they expand the skill's effective activation surface and can misroute conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The default prompt is broadly phrased and appears to encourage implicit routing for a wide range of user requests related to software, data, OpenAPI, Swagger, API documentation, workflows, artifacts, and analysis. Combined with allow_implicit_invocation=true, this can cause the skill to activate in contexts the user did not clearly intend, increasing the risk of prompt-scope overreach, unexpected data exposure to the skill, or unsafe delegation decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger scope is ambiguous because it describes a broad requirement rather than concrete, bounded invocation conditions. This makes the skill easier to activate accidentally or via loosely related prompts, which can misroute user requests and expand the skill's influence beyond its safe operational scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is phrased so broadly that it can match ordinary user requests outside the intended OpenAPI-documentation use case. Overbroad activation increases the chance this skill is invoked in the wrong context, causing unintended instruction injection into unrelated tasks and reducing routing integrity.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The file is presented as a Chinese README, but key user-facing descriptive content and trigger phrases are written in English without any note that the user may choose language or that English is required. This can conflict with language/locale expectations for a localized skill description.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The example trigger sentences use natural language patterns like 'Help me' and 'I need a practical workflow' that are common across ordinary user requests. Because they are weakly scoped, they can teach or reinforce overly permissive invocation behavior, leading to accidental matching of unrelated prompts.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.