Back to skill

Security audit

WhenToMeet

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only WhenToMeet API skill, but it exposes deletion and sensitive scheduling/account data endpoints without enough user-control guidance.

Install only if you intend agents to manage a WhenToMeet account through its API. Use a scoped API key if available, ask for explicit confirmation before deletion or cancellation, and avoid retrieving participant, booking, or connected-calendar account details unless the user specifically requested that information.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

POST /api/v1/events

bash
curl -X POST "https://whentomeet.io/api/v1/events" \
  -H "Authorization: Bearer sk_YOUR_API_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 272)May include surrounding context.

POST /api/v1/events

bash
curl -X POST "https://whentomeet.io/api/v1/events" \
  -H "Authorization: Bearer sk_YOUR_API_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documents retrieval of participant responses and connected calendar-related information without any privacy warning or minimization guidance. Participant availability and identity data can be sensitive, and exposing it through an agent may lead to over-collection or disclosure beyond what is needed for scheduling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation includes a destructive delete operation without warning, confirmation guidance, or discussion of reversibility. In an agent-driven workflow, this raises the risk of accidental or unauthorized deletion of scheduling data through ambiguous prompts or automation mistakes.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill is presented as a group scheduling integration, but it also documents account-level bookings, calendar connection enumeration, and analytics endpoints that broaden access beyond the stated purpose. This scope expansion increases the chance that an agent using the skill will access unrelated sensitive account data without clear user intent or least-privilege boundaries.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Enumerating connected calendar accounts is not necessary for basic group scheduling and exposes sensitive account metadata about a user's linked providers. In an agent context, this can enable unnecessary account discovery and privacy leakage, especially if done without a specific user request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The Get Event response includes participant names and availability responses, and List Calendar Connections returns connected account emails, which are sensitive user data elements. The markdown describes these behaviors but provides no warning about privacy-sensitive access or handling, which fits SQP-2 for markdown files.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The Delete Event endpoint states that it permanently deletes an event and all associated data, but the document does not provide an explicit caution or warning emphasizing the destructive and irreversible nature of the action. For markdown files, SQP-2 covers omitted warnings for behaviors that could affect user data or system integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown API reference documents public.createBooking collecting attendeeName and attendeeEmail, and public.getBookingDetails retrieving booking details, but it does not include any warning about handling personal data or privacy implications. For markdown files, SQP-2 applies when descriptions omit warnings about behaviors that could affect user data or privacy.

Content

No source excerpt is available for this finding.