Security audit
Security checks for vulnerabilities and agentic risk
This skill clearly provides Outgoing-powered activity search plus optional ticket booking and reservations, with the main risks disclosed and tied to its purpose.
Install only if you are comfortable sharing outing searches, location hints, and any booking details with Outgoing. Use dry-run tokens while testing, and require explicit confirmation before any real ticket purchase, reservation deposit, or no-show hold.
The description emphasizes search and convenience but does not prominently warn that the skill can make bookings and reservations that may affect user accounts or spend money. In an agent setting, this omission is dangerous because users or orchestrators may treat the skill as informational only, increasing the chance of unintended transactional actions.
The skill is framed as a general everyday concierge for broadly phrased requests, which increases the chance it will be invoked in situations where the user did not specifically intend to use an external third-party service. Because the skill can lead to downstream booking and reservation actions, overly broad invocation language raises the risk of surprise activation, unnecessary data sharing, and action-taking in a sensitive commerce context.
The 'When to use' section includes the standalone trigger term 'accessible', which is common everyday language and not specific enough to this skill's wheelchair/step-free venue-search purpose. This broad phrasing could cause unintended invocation for unrelated accessibility topics.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
POST /partner/v1/bookingscurl -sS -X POST https://api.outgoing.world/partner/v1/bookings \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
-H "Content-Type: application/json" \
-d '{
The skill's trigger phrases are broad everyday terms like 'restaurant', 'dinner', and 'lunch', which can cause the skill to activate in many ordinary conversations that are not explicit requests to use a third-party service. Because this skill sends user queries to an external API, overbroad invocation increases the chance of unintended data disclosure and unnecessary third-party calls.
This skill instructs the agent to transmit natural-language user prompts and optional location data to an external service at api.outgoing.world. That is expected for the feature, but it is still a real security/privacy boundary crossing: sensitive user preferences, plans, and potentially precise location may be disclosed to a third party if sent without minimization or user awareness.
curl -sS -G https://api.outgoing.world/partner/v1/search \
-H "Authorization: Bearer $OUTGOING_API_KEY" \
--data-urlencode "prompt=great dinner spots for tonight — lively but easy to talk" \
--data-urlencode "city=new_york"
The listed triggers include generic terms like "nature," "outdoors," "park," and "garden," which are common words that could appear in many unrelated conversations. The file does not provide exclusion conditions or narrower invocation constraints, increasing the chance of unintended activation.
The listed triggers include generic phrases such as "with friends," "fun bars," and "happy hour," which overlap with common conversational requests and are not tightly scoped to this specific skill. The description does not provide exclusion conditions or negative examples to clarify when the skill should not activate.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
env:
- OUTGOING_API_KEY
anyBins:
- curl
envVars:
- name: OUTGOING_API_KEY
required: true
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
env:
- OUTGOING_API_KEY
anyBins:
- curl
envVars:
- name: OUTGOING_API_KEY
required: true
The listed triggers include very generic phrases such as "make friends" and "social events," which can arise in many ordinary conversations and may cause the skill to activate outside a clearly bounded context. The description does not provide exclusion conditions or negative examples to clarify when these phrases should not invoke the skill.
The trigger list includes phrases like "can I bring my dog" and especially "somewhere with my pet," which are broad natural-language expressions that could arise in many casual contexts. The file does not provide exclusion conditions or tighter activation constraints to distinguish when this skill should activate versus more general recommendation skills.
The activation guidance includes broad terms like "active," "sporty," and "something to get moving," which can overlap with ordinary conversation and many unrelated user intents. The file does not provide exclusion conditions or narrower constraints to distinguish when this skill should activate versus when a different discovery skill should be used.