Security audit

Discover Events in Any City

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Outgoing API integration for finding activities and booking tickets, with privacy and payment-handling cautions users should review.

Install only if you are comfortable sending search prompts, city or precise-location hints, and a user-linked identifier to Outgoing. Use a pseudonymous service-specific user ID rather than an email or raw account ID, avoid confidential details in prompts, and require clear confirmation before using any real payment token or submitting a paid booking.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (7)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill instructs sending an end-user identifier (via `X-External-User-Id`) to a third-party API but does not include an explicit privacy notice, minimization guidance, or constraints on what identifier may be used. This creates a real privacy and compliance risk because implementers may transmit stable or directly identifying user data to an external service without informed consent or appropriate safeguards.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill instructs the agent to send a persistent end-user identifier on every API call but provides no guidance about notice, consent, minimization, or how that identifier should be generated. Because this skill handles potentially sensitive behavioral data about romantic activities, linking searches to a stable external user ID creates a privacy risk and could enable tracking or profiling if implemented as written.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly instructs sending user search prompts and a persistent user-linked identifier (`external_user_id` / `X-External-User-Id`) to a third-party API, but does not include any user-facing privacy notice, consent flow, or data-minimization guidance. This creates a real privacy and compliance risk because location/search intent and stable identifiers can reveal sensitive behavioral patterns and be transmitted off-platform without clear disclosure.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs operators to provision each end user and send an `external_user_id` in the `X-External-User-Id` header on every request to a third-party API, but it does not include a clear user-facing privacy disclosure or consent guidance. This can cause silent transmission of user-linked identifiers to an external service, creating privacy and compliance risk, especially when combined with location- or preference-based queries.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs operators to provision persistent end-user identifiers and send them to a third-party API on every call, but it does not include any explicit privacy notice, consent flow, or data-minimization guidance. This creates a real privacy and compliance risk because user-linked activity queries may reveal location, habits, or preferences to an external service without transparent disclosure.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill instructs the agent to provision end users and send user-linked identifiers and search context to a third-party API, but it provides no user-facing disclosure, consent flow, or data-minimization guidance. This can lead to silent transmission of personal or behavioral travel data to an external service, creating privacy and compliance risk.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill instructs operators to provision users and send an external_user_id to a third-party API on every call, but it does not disclose this data-sharing behavior or advise minimizing identifier sensitivity. This can expose persistent user-linked metadata to an external service without transparency, increasing privacy and compliance risk, especially if the identifier is directly identifying or reused across systems.

Static analysis

No suspicious patterns detected.