Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation helper for OpenAPI/Swagger work; its main issue is loose auto-invocation wording, not hidden or harmful behavior.

This skill is reasonable to install for OpenAPI or Swagger documentation tasks. Be aware it may activate on broad REST API or API documentation wording, so users who want tighter routing should invoke it explicitly or narrow its trigger phrases before publishing in a shared environment.

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: 96% confidence
Finding: The trigger phrases are generic and patterned as broad natural-language requests, which increases the chance the skill is invoked when a user did not explicitly intend to call it. In an agent ecosystem, unintended invocation can cause context hijacking, misrouting, or execution of the wrong workflow, especially because the skill targets common API-documentation terms like OpenAPI, Swagger, and REST API.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad, repetitive, and loosely scoped, which can cause the skill to activate in contexts beyond the user's actual intent. In an agent environment, overbroad activation increases the chance of unintended invocation, confusing task routing, or misuse of the skill for adjacent requests that were not meant to involve OpenAPI documentation workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description uses broad activation terms such as 'software-and-data' and generic requests for workflows, analysis, or implementation support, which can cause the skill to match many unrelated prompts. Over-broad routing is dangerous because it can hijack requests outside OpenAPI documentation, leading to incorrect tool/skill selection and increasing the chance that the agent follows irrelevant or lower-safety instructions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example triggers use generic phrasing like 'Help me' and 'I need a practical workflow' with only weak domain anchoring, which can activate the skill from commonplace language. This increases accidental invocation risk and may cause the agent to route general requests into this skill even when the user did not intend OpenAPI documentation assistance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation description is broad and mixes generic software terms with common documentation topics, which can cause the skill to trigger in conversations that are not specifically asking for this workflow. Over-broad routing increases the chance of unintended invocation, context hijacking, and responses shaped by the skill when a narrower or different skill should apply.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list includes broad phrases like 'software-and-data', 'api documentation', and 'rest api' without scoping constraints, so ordinary technical discussions may accidentally activate this skill. If exploited or simply misrouted, the agent may prioritize this skill's instructions over more appropriate domain logic, degrading reliability and enabling prompt-routing abuse.
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 visible trigger constraints, exclusions, or narrowing conditions, which can cause the agent to auto-select this skill in broader conversations than intended. That increases the chance of prompt-scope confusion, unreviewed tool activation, or unintended exposure of user/API-related content to a skill that was not explicitly requested.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The invocation examples do not clearly limit when the skill should run and instead present broad natural-language templates that could match many benign requests. This weak activation boundary can lead to accidental skill invocation, misrouting, and exposure of the agent to unnecessary instruction context from the skill during unrelated conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentence is so generic that it can activate on ordinary user phrasing rather than an explicit request to use this skill. Over-broad activation increases the chance the agent routes unrelated prompts into this skill, which can cause prompt-scope confusion, unintended behavior, or make downstream prompt-injection opportunities easier to reach.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This is a zh-CN README, but key descriptive and trigger content is presented in English, which can effectively impose a language choice on users expecting Chinese-only guidance. The file does not explicitly offer a language option or explain the mixed-language requirement.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The example trigger phrases use generic helper language like 'Help me' and 'I need a practical workflow', which overlaps with normal user requests and may train routing systems toward over-activation. While less severe than the keyword issue, these examples still blur the intended boundary and can contribute to accidental invocation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.