ClawHub
Back to skill

Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-assistance skill with broad activation wording but no code execution, persistence, credential access, or hidden data movement.

Installers should be aware that this skill may activate for broad API-documentation-related wording because implicit invocation is enabled and the triggers are not tightly scoped. For sensitive repositories, invoke it explicitly when you want OpenAPI or Swagger documentation help and review any proposed code or documentation changes before applying them.

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 (12)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The default prompt is extremely broad and maps to common terms like software, data, OpenAPI, Swagger, API documentation, and REST API, which are likely to appear in many ordinary requests. When paired with implicit invocation, this can cause the skill to activate outside narrowly intended contexts, increasing the chance of unintended prompt injection exposure, irrelevant tool use, or routing sensitive user content into the skill unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

Enabling implicit invocation without strict trigger constraints allows the platform to auto-route user requests into this skill based on loose semantic overlap. In this skill, the broad documentation and API-related scope makes accidental activation more likely, which can expose unrelated prompts or context to the skill and amplify the impact of any unsafe instructions or downstream actions.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger keywords include very broad terms like 'software-and-data' and generic phrases such as 'needs a practical workflow, artifact, checklist, analysis, or implementation support,' which can match many unrelated requests. This can cause unintended activation of the skill outside its intended OpenAPI/Swagger scope, leading to misrouting, prompt-surface expansion, and reduced reliability of skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger sentences are generic and loosely scoped, which can cause the skill to activate for broad API- or documentation-related prompts that do not specifically require this capability. In an agent environment, overbroad activation can misroute user requests, override more appropriate skills, or unnecessarily expose the model to additional instruction content, increasing the chance of incorrect or unsafe task handling.

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 and partially template-like, covering common terms such as OpenAPI, Swagger, API documentation, and REST API without enough narrowing context. This can cause unintended skill activation, leading the agent to apply this skill in unrelated requests and potentially override a more appropriate workflow or produce irrelevant guidance.

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 a wide range of software and API-related requests, which can cause the wrong skill to be invoked. Over-broad routing is dangerous because it can override more appropriate skills, produce irrelevant guidance, and expand the attack surface for prompt-confusion or unintended tool use in adjacent domains.

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 generic terms such as 'software-and-data' and broad API phrases that are not sufficiently constrained to documentation-generation use cases. This increases the chance of accidental invocation on unrelated user requests, reducing routing precision and potentially exposing users to incorrect workflows or prompt-scope confusion.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description uses broad trigger terms such as software-and-data, openapi, swagger, api documentation, and rest api without strong boundary conditions. This can cause the skill to activate for loosely related requests, increasing the chance of inappropriate routing, irrelevant assistance, or accidental exposure of guidance outside the intended scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example trigger phrases begin with highly generic language like 'Help me' and 'I need a practical workflow,' which may match ordinary conversation patterns. In systems that rely on trigger examples or fuzzy matching, this can lead to accidental invocation and misrouting of user requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger sentences are templated and ambiguous, repeating a long requirement description rather than expressing concrete user intents a router can distinguish. Because the activation scope is unclear, normal user requests may spuriously invoke this skill, which increases the chance of incorrect handling and makes downstream behavior less predictable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file is a Chinese-language README and does not indicate that language selection is optional or that alternative locales are available within the skill description. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the constraint is clearly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example trigger sentences are malformed and vague, which weakens activation clarity and makes the routing behavior harder to predict or validate. While less severe than broad descriptions or keywords, ambiguous examples can still mislead maintainers and contribute to inconsistent skill selection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.