Security audit

Create secure videoconference

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to generate Meetling meeting links and invite/share text without hidden network calls, persistence, or automatic sending.

Install only if you want a local helper that reads optional ./contacts.json recipient mappings and produces Meetling links plus invite/share text. Review generated recipients before any Claw sending path uses the returned share payload, especially because participant names without a start time are treated as an instant call.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The instant-call trigger rules are broad and can activate on ordinary conversational phrases like 'now', 'asap', or merely the presence of participants without a start time. That can cause unintended meeting creation and message sharing to recipients, which is a security-relevant action because it may send links or notifications without sufficiently clear user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The language is inferred automatically from input text and falls back to SKILL_LANGUAGE_DEFAULT when detection is ambiguous. This can force German or English output without the user explicitly choosing a language, which is a locale policy concern under the stated rules.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The markdown includes an example that supplies participants' email addresses and meeting details via stdin, which indicates the skill may process personal contact data. The README does not include any warning about privacy implications, where that data goes, or whether external services are contacted.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The README states SKILL_LANGUAGE_DEFAULT (default: en), which suggests the skill may default responses or behavior to English. Under the stated policy, forcing or defaulting to a specific language without clear user opt-in can be a locale/language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The manifest declares SKILL_LANGUAGE_DEFAULT, which indicates the skill may enforce a language or locale default. The file does not mention any user choice, opt-in, or justification for this locale behavior, which can conflict with language policy expectations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This code loads participant contact mappings from ./contacts.json, which is access to user/system data relevant to meeting recipients. Although the code comments document the behavior for developers, there is no user-facing prompt, log, or other disclosure in the runtime output that the skill reads local contacts data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.