ClawHub
Back to skill

Security audit

API Design

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain REST API design reference and does not appear to run code or access data.

Install this if you want Codex to provide REST API design conventions. Be aware it may be selected automatically for API-related work, so review its advice against your project's existing API standards before applying it.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (3)

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 · SKILL.md (reported line 31)May include surrounding context.

md
POST   /api/v1/users
PUT    /api/v1/users/:id
PATCH  /api/v1/users/:id
DELETE /api/v1/users/:id

# Sub-resources for relationships
GET    /api/v1/users/:id/orders

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

Enabling implicit invocation without defined activation boundaries allows the skill to be auto-selected based on broad semantic similarity rather than explicit user intent. Because this skill covers a wide production-facing domain, unintended invocation could influence architecture recommendations, override more appropriate skills, or expose users to off-target guidance in sensitive engineering workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The default prompt is very broad and generic, which increases the chance that the platform may invoke this skill for loosely related user requests. In combination with weak trigger constraints, this can cause unintended routing, over-application of the skill, or responses shaped by the skill when the user did not clearly request API design guidance.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:302