Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only OpenAPI helper skill with some overly broad trigger wording, but no evidence of hidden execution, data access, persistence, or destructive behavior.

Installers should know this skill may activate for broad API-documentation phrasing. It is otherwise limited to helping with OpenAPI/Swagger documentation workflows and does not include executable code or persistence.

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 (10)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is so broad and malformed that it can match routine user phrasing unrelated to an intentional invocation, causing the skill to activate outside its intended scope. In an agent environment, overbroad activation can route benign requests into a workflow that makes assumptions, asks for unnecessary inputs, or produces documentation-oriented outputs when the user asked for something else.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentences are generic enough that normal conversation about OpenAPI, Swagger, or REST API documentation could activate the skill unintentionally. In an agent ecosystem, over-broad invocation can cause the wrong skill to take control, leading to incorrect actions, context leakage to an unintended skill, or bypass of more appropriate guardrailed workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger phrases are broad, templated, and partially generic, which increases the chance the skill is invoked when a user did not explicitly intend to use it. In an agent ecosystem, unintended invocation can route user data or workflow control to the wrong skill, causing confusion, incorrect actions, or accidental processing of sensitive API-related context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is broad enough to activate on generic software, data, API, or documentation requests that may not actually require OpenAPI-specific help. Over-broad routing can cause the wrong skill to engage, leading to irrelevant guidance, prompt-scope confusion, and increased exposure to downstream instruction conflicts from unintended contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keywords include broad phrases such as 'software-and-data' and general API-related terms that can match many unrelated requests. This weakens routing precision and may invoke the skill in inappropriate situations, producing misleading outputs or interfering with better-matched skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description and usage criteria are broad enough to match many ordinary technical conversations containing terms like OpenAPI, Swagger, or API documentation. This can cause the skill to activate outside its intended scope, leading to irrelevant instruction injection, response steering, or unreviewed workflow application in contexts where the user did not explicitly request this specialized behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger section relies mainly on keywords and example phrases without defining scope limits or negative examples, which increases the chance of false activation. Over-broad routing is dangerous because it can apply the skill's workflow and assumptions to unrelated prompts, potentially overriding better-matched skills or causing unintended handling of user requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt is broadly phrased and can trigger the skill for a wide range of loosely related requests without clear boundaries, increasing the chance of unintended invocation. Because this skill influences software/API documentation workflows, overbroad activation could cause the agent to apply the skill in contexts where its assumptions or outputs are not appropriate, leading to misleading guidance or prompt-scope confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger is ambiguous about when the skill should activate and does not clearly bound the request type, which increases the chance of accidental or incorrect invocation. Ambiguous routing in skills is dangerous because it can override more appropriate tools, degrade reliability, and create opportunities for prompt-scope confusion when common phrasing is treated as a specialized instruction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The file is presented as a Chinese README but includes substantial English content in key user-facing sections such as the requirement description, workflow description, and trigger phrases. This can amount to forcing a language/locale without user opt-in or an explicit justification.
Content: No source excerpt is available for this finding.