T08 · Insecure Dependencies
- Location
SKILL.md:51- Finding
Unpinned Third-Party Package Installation and Remote Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to connect to TIDY as described, but it gives broad, long-lived access to sensitive property-management data and destructive actions with weak safety guidance.
Install only if you are comfortable giving an agent broad TIDY account access, including creating, changing, cancelling, and deleting property-management records. Protect TIDY_API_TOKEN like a password, avoid passing live tokens on command lines, prefer pinned package versions or a reviewed install path, and require explicit confirmation before any delete, cancellation, or booking change.
SKILL.md:51Unpinned Third-Party Package Installation and Remote Execution
references/authentication.md:57Non-Expiring Bearer Tokens Remain Valid After Reauthentication
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
DELETE /api/v2/addresses/:address_id
Active jobs must be cancelled first.
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
DELETE /api/v2/guest-reservations/:guest_reservation_id
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
DELETE /api/v2/tasks/:task_id
The skill promotes persistent authenticated use through stored credentials and non-expiring tokens, which increases exposure if a local machine or account is compromised. In a property-management context, persistent sessions can enable unauthorized scheduling, cancellations, address access-note retrieval, and other impactful actions without re-authentication.
tidy-request "Schedule a deep clean for next Tuesday at my Beach House" tidy-request "Create a guest reservation for April 10-14" tidy-request "Report a broken window at address 123" --address-id 123
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# Get a token
curl -X POST https://public-api.tidy.com/api/v2/auth/login \
-H "Content-Type: application/json" \
-d '{"email":"you@example.com","password":"yourpassword"}'
# Returns: { "token": "abc123..." }
The documentation states that tokens do not expire and that credentials are stored locally, but it provides no security or privacy warning about long-lived bearer tokens and filesystem credential storage. Stolen tokens or readable credential files could grant persistent account access and unauthorized property-management actions.
The MCP tool list includes destructive capabilities such as delete_address, cancel_booking, delete_guest_reservation, and delete_task without any warning, confirmation guidance, or safety notes. In an agent setting, this increases the chance of unintended destructive actions against real properties, reservations, and maintenance records.
The skill instructs users to execute npx @tidydotcom/mcp-server without pinning an exact package version. This creates a supply-chain risk because a future compromised or breaking package release would be fetched and executed automatically at runtime.
The second npx @tidydotcom/mcp-server example also pulls and runs the latest package code with access to a supplied API token. If the upstream package is ever compromised, users could expose credentials or execute attacker-controlled code locally.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X POST https://public-api.tidy.com/api/v2/message-tidy \
-H "Authorization: Bearer $TIDY_API_TOKEN" \
-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.
curl -X POST https://public-api.tidy.com/api/v2/addresses \
-H "Authorization: Bearer $TIDY_API_TOKEN" \
-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.
curl -X POST https://public-api.tidy.com/api/v2/jobs \
-H "Authorization: Bearer $TIDY_API_TOKEN" \
-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.
curl -X POST https://public-api.tidy.com/api/v2/guest-reservations \
-H "Authorization: Bearer $TIDY_API_TOKEN" \
-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.
curl -X POST https://public-api.tidy.com/api/v2/tasks \
-H "Authorization: Bearer $TIDY_API_TOKEN" \
-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.
curl -X POST https://public-api.tidy.com/api/v2/auth/signup \
-H "Content-Type: application/json" \
-d '{
"first_name": "Jane",
The reference instructs clients to send raw account credentials via the login tool and arbitrary freeform property-management messages via message_tidy to a remote API, but it provides no warning about the sensitivity of credentials, reservation data, guest information, or operational details. In an AI-agent context, this omission increases the chance that users or downstream agents will transmit secrets and personal data without informed consent or minimization, leading to privacy, credential-handling, and data-exposure risks.
This markdown file describes destructive operations such as deleting addresses and notes only a prerequisite about active jobs, but it does not warn users about the impact on stored data or the irreversible nature of deletion. Similar destructive endpoints elsewhere in the document are also presented without any user-facing caution, which can omit important safety context in a skill description.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Example:
curl -X POST https://public-api.tidy.com/api/v2/jobs \
-H "Authorization: Bearer YOUR_TOKEN" \
-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.
Example:
curl -X POST https://public-api.tidy.com/api/v2/guest-reservations \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{