Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation workflow skill for OpenAPI/Swagger work, with no executable payload or hidden persistence, though its activation wording is broader than ideal.

Install only if you want an agent to help with OpenAPI, Swagger, or REST API documentation tasks. Be aware that its broad implicit triggers may activate it for general API conversations, so users who want tighter routing should narrow the trigger wording or disable implicit invocation.

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
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
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

Findings (13)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · README.md (reported line 18)May include surrounding context.
md
## 来源证据 - github-issues：[[Backend] Provide a transaction-status and reconciliation API for clients](https://github.com/Cylo-Traders/Agrocylo-Global/issues/449) - github-issues：[Add `DELETE /api/webhooks/:id` route with confirmation token and cascading delivery cleanup](https://github.com/CalloraOrg/Callora-Backend/issues/425) - github-issues：[Export an OpenAPI specification artefact](https://github.com/Adamantine-guild/guildpass-core/issues/49) - github-issues：[Add `POST /api/apis/:id/endpoints/bulk` to register multiple endpoints atomically through `apiRepository`](https://github.com/CalloraOrg/Callora-Backend/issues/400) - github-issues：[Add cursor-based pagination to `GET /api/usage` to replace offset/limit on large windows](https://github.com/CalloraOrg/Callora-Backend/issues/406)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · README.zh-CN.md (reported line 18)May include surrounding context.
md
## 来源证据 - github-issues：[[Backend] Provide a transaction-status and reconciliation API for clients](https://github.com/Cylo-Traders/Agrocylo-Global/issues/449) - github-issues：[Add `DELETE /api/webhooks/:id` route with confirmation token and cascading delivery cleanup](https://github.com/CalloraOrg/Callora-Backend/issues/425) - github-issues：[Export an OpenAPI specification artefact](https://github.com/Adamantine-guild/guildpass-core/issues/49) - github-issues：[Add `POST /api/apis/:id/endpoints/bulk` to register multiple endpoints atomically through `apiRepository`](https://github.com/CalloraOrg/Callora-Backend/issues/400) - github-issues：[Add cursor-based pagination to `GET /api/usage` to replace offset/limit on large windows](https://github.com/CalloraOrg/Callora-Backend/issues/406)

Tool Parameter Abuse

High

Category: Tool Misuse
Confidence: 80% confidence
Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Content: Scanner excerpt · references/requirement-plan.md (reported line 36)May include surrounding context.
md
## 来源证据 - github-issues：[[Backend] Provide a transaction-status and reconciliation API for clients](https://github.com/Cylo-Traders/Agrocylo-Global/issues/449) - github-issues：[Add `DELETE /api/webhooks/:id` route with confirmation token and cascading delivery cleanup](https://github.com/CalloraOrg/Callora-Backend/issues/425) - github-issues：[Export an OpenAPI specification artefact](https://github.com/Adamantine-guild/guildpass-core/issues/49) - github-issues：[Add `POST /api/apis/:id/endpoints/bulk` to register multiple endpoints atomically through `apiRepository`](https://github.com/CalloraOrg/Callora-Backend/issues/400) - github-issues：[Add cursor-based pagination to `GET /api/usage` to replace offset/limit on large windows](https://github.com/CalloraOrg/Callora-Backend/issues/406)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is malformed and broad enough to match ordinary requests about OpenAPI or API documentation without clearly requiring explicit invocation of this skill. Over-broad routing can cause the agent to activate in unintended contexts, increasing the chance of irrelevant or unsafe task handling and reducing user control over which capability is used.
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 template-like, so the skill may activate on loosely related requests instead of clear user intent. In an agent ecosystem, overly broad invocation increases the chance of inappropriate context capture or unintended guidance being injected into unrelated workflows.
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 broad and generic, including free-form text and a direct '$openapi-docs-generator' invocation pattern that could cause the skill to activate in contexts not specifically requesting this capability. In an agent environment, overbroad routing increases the chance of unintended invocation and prompt-scope confusion, which can expose unrelated user tasks to this skill's instructions or outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description and trigger guidance are broad enough to match many generic software-help requests, which can cause the agent to invoke this skill outside its intended OpenAPI/Swagger documentation niche. Over-broad activation increases the chance of misrouting user requests, producing irrelevant guidance, and allowing this skill to overshadow more appropriate skills.
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 very generic wording such as 'Help me' and 'I need a practical workflow,' which overlaps with ordinary user requests and can lead to accidental invocation. In an agent ecosystem, ambiguous example triggers broaden the matching surface and make routing less predictable and less safe.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger description is broad enough that ordinary conversations about APIs, Swagger, or documentation could activate the skill unintentionally. In an agent system, over-broad routing can expose users to irrelevant instructions, cause unintended file or workflow actions, and increase the attack surface for prompt-injection through accidental skill invocation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The keyword list is ambiguous and lacks exclusion criteria, so common technical terms like 'openapi', 'swagger', or 'rest api' may match routine discussions that do not actually request this skill. This increases unintended invocation risk, which can misroute conversations, override better-suited skills, and make prompt-routing easier to manipulate with crafted keyword stuffing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill enables implicit invocation with no trigger constraints, exclusions, or narrowing conditions, which can cause the agent to invoke this skill in broader contexts than intended. That increases the risk of prompt-scope confusion, unintended routing, and misuse of the skill on inputs that only loosely match OpenAPI-related requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation examples are ambiguous, truncated, and do not clearly define when this skill should be selected versus generic development assistance. This can lead to misrouting or accidental activation, which is dangerous in multi-skill systems because it weakens isolation and may route sensitive user requests into an ill-fitting workflow.
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 'SKILL.md: English skill instructions' alongside a Chinese variant, but the README does not explain how language selection occurs or whether users can opt in to a preferred language. This can create an implicit language-default policy issue if English is used automatically without user choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.