Security audit

TG Cam Skill

Security checks for vulnerabilities and agentic risk

Overview

This camera skill is purpose-aligned, but it persists sensitive camera API credentials and exposes home surveillance images/events with limited consent and privacy guardrails.

Install only if you trust the camera service and are comfortable giving the skill access to snapshots, event images, and device status. Avoid pasting API keys unless you intend them to be saved, keep openclaw.json private, and rotate the camera API key if that file may have been shared or committed.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:41
Finding: Camera API Credentials Persisted in Plaintext Configuration
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:68
Finding: Untrusted Remote Notice Content Relayed Through Agent Responses
Content: View full analysis
Remediation: View remediation

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 (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill handles highly sensitive home surveillance data, including live snapshots and event images, but the description does not clearly warn that these outputs may reveal private household activity, occupants, visitors, or routines. Without an upfront privacy warning, users may invoke the skill without appreciating the sensitivity of the data being retrieved and displayed.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill includes broad, everyday trigger phrases such as requests to 'see what happened today' or 'take a look now,' which can cause unintended invocation in ambiguous conversations. In the context of a home camera skill, accidental activation can expose sensitive visual data, device status, or event history without sufficiently explicit user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The manifest description is entirely in Chinese, and the document consistently instructs behavior and outputs in Chinese without indicating that users may choose another language. This can violate language/locale policy when no opt-in or region-specific justification is provided.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.