Security audit

Code Mirror

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward code-generation guide for mirroring frontend and backend code, with no hidden execution, persistence, or data exfiltration behavior found.

Install this if you want an agent to inspect application code and generate matching frontend or backend files. Review generated CRUD, auth, database, and migration code before applying it to a real project, especially where delete routes or account data are involved.

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 (5)

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 76)May include surrounding context.
axios.get('/api/users') // GET /api/users → User[] axios.post('/api/users', { name, email }) // POST /api/users → User axios.put(/api/users/${id}, { name }) // PUT /api/users/:id → User axios.delete(/api/users/${id}) // DELETE /api/users/:id fetch('/api/users?page=1&limit=20') // GET with query params

text

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 833)May include surrounding context.
axios.get('/api/users') // GET /api/users → User[] axios.post('/api/users', { name, email }) // POST /api/users → User axios.put(/api/users/${id}, { name }) // PUT /api/users/:id → User axios.delete(/api/users/${id}) // DELETE /api/users/:id fetch('/api/users?page=1&limit=20') // GET with query params

text

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 139)May include surrounding context.
@router.get("/users/{user_id}") # GET /users/:id → UserOut @router.post("/users") # POST /users → UserOut @router.put("/users/{user_id}") # PUT /users/:id → UserOut @router.delete("/users/{user_id}", status_code=204) # DELETE /users/:id → 204

text
**2. Data Models / Schemas** — database models and API schemas

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description says it should be invoked for broad goals like mirroring, syncing, or scaffolding code across the stack without tight boundaries. This can cause over-triggering on common software requests, leading the agent to read more workspace context than necessary and generate code in situations where a narrower skill should have been used.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The listed trigger phrases include generic terms such as 'mirror', 'bridge', 'generate counterpart', and 'generate client' with no scope constraints. In an agentic environment, ambiguous triggers increase the chance of accidental activation and inappropriate access to project files or code generation steps based on loosely related user prompts.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.