Security audit

Wyze Cam

Security checks for vulnerabilities and agentic risk

Overview

This Wyze camera skill is mostly purpose-aligned, but it needs review because it can access private camera imagery, control security devices, install unpinned packages, and write snapshots to caller-chosen paths.

Review before installing. Use this only in an environment where the agent should have access to Wyze credentials, camera images, and device controls. Prefer explicit camera requests, confirm state-changing actions, and avoid passing arbitrary snapshot output paths. Pin dependencies or install from a reviewed lockfile where possible.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: scripts/package.json:5
Finding: Unpinned Third-Party Runtime Dependencies
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/cam:75
Finding: Arbitrary Writable-Path Overwrite Through Snapshot Output Argument
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill exposes environment-backed capabilities and setup instructions involving secrets (WYZE_EMAIL, WYZE_KEY_ID, WYZE_API_KEY, token directories) but does not declare explicit tool scope or permissions boundaries. In an agent environment, missing scope declarations can allow the model to invoke the skill or access sensitive configuration more broadly than intended, increasing the risk of unintended secret use or device control.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation guidance is broad enough to trigger on ordinary phrases like 'show me the driveway' or 'see a camera,' which can cause the agent to activate surveillance functionality from ambiguous conversational requests. Because this skill can retrieve camera imagery and control physical/security-related devices, overbroad routing raises the chance of privacy-invasive snapshots or unintended device actions without clear, informed user intent.
Content: No source excerpt is available for this finding.

Unpinned Dependencies

Low

Category: Supply Chain
Confidence: 40% confidence
Finding: Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
Content: Scanner excerpt · scripts/package.json (reported line 6)May include surrounding context.
json
"private": true, "description": "Runtime dependency for the Wyze camera OpenClaw skill", "dependencies": { "wyze-node": "^2.12.2" }, "comment": "Live `snapshot` also needs optional WebRTC deps: npm install werift ws ffmpeg-static" }

Static analysis

No suspicious patterns detected.