Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable OpenAPI/Swagger documentation helper with broad triggers that may cause occasional unwanted activation but no hidden or high-impact behavior found.

This skill appears safe to install for OpenAPI or Swagger documentation work. Be aware that its generic triggers may make it activate when you only meant a broader API or developer-experience discussion; explicit invocation is preferable for predictable 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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 keywords include very broad terms such as 'software-and-data' and 'api documentation', which can match many unrelated user requests and cause the skill to activate outside its intended scope. Over-broad activation can route benign conversations into this skill unexpectedly, leading to irrelevant guidance, prompt-surface expansion, and increased exposure to adversarial inputs from unrelated contexts.
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 generic and mechanically templated, making it easier for unrelated user requests containing common terms like OpenAPI, Swagger, or practical workflow to invoke the skill unintentionally. In an agent system, over-broad activation can route user input into the wrong capability, causing inappropriate instructions, confusing outputs, or unsafe context mixing across tasks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This file is a Chinese-language README variant ('README.zh-CN.md') and presents the skill content in Simplified Chinese without any indication that the user can choose another language or locale within this document. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the constraint is clearly documented and justified.
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 extremely generic and can match ordinary user requests such as asking for help or a workflow, which increases the chance of unintended skill activation. In an agent environment, over-broad invocation can route unrelated prompts into this skill, causing incorrect task handling, context leakage across skills, or bypass of the user's actual intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description and usage guidance are broad enough that the skill may activate for general software or API-related requests beyond narrowly scoped OpenAPI documentation tasks. Over-broad activation can cause incorrect routing, unnecessary context loading, or an unintended skill taking control of requests where more specialized safeguards or logic should apply.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The keyword list includes broad and commonly occurring technical terms such as 'openapi', 'swagger', 'api documentation', and 'developer experience', which can appear in many benign engineering conversations. This increases the chance of false activation and context collision, potentially causing the agent to apply this skill in situations it was not designed to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords include broad, generic terms such as "software-and-data" and common API-related phrases, which can cause the skill to be invoked outside its intended scope. Over-broad activation increases the chance of prompt-routing mistakes, irrelevant guidance, and accidental exposure of this skill in contexts where a narrower tool should be used.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger sentences use very broad lead-ins like "Help me" and "I need a practical workflow for", which provide little boundary-setting and can train or encourage overly permissive invocation behavior. In practice, this can increase false activations and misrouting, especially when combined with already-generic keywords.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill metadata uses broad, loosely constrained invocation language in both the description and default prompt, which can cause the agent to activate this skill for a wide range of software or API-related requests beyond its intended scope. When combined with allow_implicit_invocation: true, this increases the chance of inappropriate routing, context leakage, or the skill influencing tasks it was not specifically selected for.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger sentence template is vague and malformed, so it does not clearly define when the skill should be invoked versus when normal assistant behavior should continue. Ambiguous activation rules increase the chance of accidental or adversarial invocation, which can degrade routing reliability and broaden the skill's effective attack surface.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The file lists separate English and Chinese instruction files, but does not state that the user can choose their preferred language or locale. Because locale policy findings apply to natural-language content, this omission can be read as an undocumented language-routing behavior rather than an explicit opt-in choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.