InspirAI API Spec

• Outcome: Review
• Latest audit: Sep 12, 2026 · 2:04 AM UTC
• Version: 1.0.0

Overview

The skill is a coherent API documentation tool, but its update workflow can automatically commit and push generated API details to a remote repository without an explicit review step.

Install only if you are comfortable with the agent reading route and handler files and maintaining a persistent API-spec registry under ~/.apispec. Before running update, review generated docs and require explicit approval before any commit or push, especially if the repository may contain internal endpoints, schemas, tokens, or business-sensitive API details.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Rogue Agent: Self-Modification, Session Persistence
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 82% confidence

Finding

This duplicated finding points to the same behavior: cloning and maintaining a long-lived local registry under ~/.apispec/registry. In the skill context, that registry contains cross-project API documentation, so persistence increases the blast radius of accidental disclosure and can cause later tasks to trust or consume stale or tampered content from prior sessions.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

如果目录不存在，提示用户 clone 仓库：

bash

mkdir -p ~/.apispec
git clone <your-api-specs-repo> ~/.apispec/registry

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 82% confidence

Finding

This duplicated finding points to the same behavior: cloning and maintaining a long-lived local registry under ~/.apispec/registry. In the skill context, that registry contains cross-project API documentation, so persistence increases the blast radius of accidental disclosure and can cause later tasks to trust or consume stale or tampered content from prior sessions.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

如果目录不存在,提示用户 clone 仓库:

bash

mkdir -p ~/.apispec
git clone <your-api-specs-repo> ~/.apispec/registry

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill instructs an automatic git push origin main as part of the update workflow without an explicit user confirmation gate or dry-run/review step. In an agent context, this can cause unintended publication of internal API documentation, route metadata, or sensitive schema details to a shared remote repository, turning a local parsing task into a data exfiltration or integrity-changing action.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

Natural-language instructions, headings, notes, and output examples are all written in Chinese, which effectively forces a specific language for users. The file does not offer an opt-in language choice or state that the skill is intentionally limited to a Chinese-language audience or region-specific context.

Content

No source excerpt is available for this finding.