Back to skill

Security audit

Tidy

Security checks for vulnerabilities and agentic risk

Overview

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.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:51
Finding

Unpinned Third-Party Package Installation and Remote Execution

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
references/authentication.md:57
Finding

Non-Expiring Bearer Tokens Remain Valid After Reauthentication

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (19)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

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).

Content

Scanner excerpt · references/rest-api-reference.md (reported line 123)May include surrounding context.

Delete Address

text
DELETE /api/v2/addresses/:address_id

Active jobs must be cancelled first.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

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).

Content

Scanner excerpt · references/rest-api-reference.md (reported line 247)May include surrounding context.

Delete Reservation

text
DELETE /api/v2/guest-reservations/:guest_reservation_id

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

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).

Content

Scanner excerpt · references/rest-api-reference.md (reported line 290)May include surrounding context.

Delete Task

text
DELETE /api/v2/tasks/:task_id

Session Persistence

Medium
Category
Rogue Agent
Confidence
78% confidence
Finding

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.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Send any property management request in plain English

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

text

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 67)May include surrounding context.

bash
# 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..." }

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

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.

Content

No source excerpt is available for this finding.

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 207)May include surrounding context.

Send a message

bash
curl -X POST https://public-api.tidy.com/api/v2/message-tidy \
  -H "Authorization: Bearer $TIDY_API_TOKEN" \
  -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 254)May include surrounding context.

Create an address

bash
curl -X POST https://public-api.tidy.com/api/v2/addresses \
  -H "Authorization: Bearer $TIDY_API_TOKEN" \
  -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 317)May include surrounding context.

Create a job

bash
curl -X POST https://public-api.tidy.com/api/v2/jobs \
  -H "Authorization: Bearer $TIDY_API_TOKEN" \
  -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 379)May include surrounding context.

Create a reservation

bash
curl -X POST https://public-api.tidy.com/api/v2/guest-reservations \
  -H "Authorization: Bearer $TIDY_API_TOKEN" \
  -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 416)May include surrounding context.

Create a task

bash
curl -X POST https://public-api.tidy.com/api/v2/tasks \
  -H "Authorization: Bearer $TIDY_API_TOKEN" \
  -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 · references/authentication.md (reported line 8)May include surrounding context.

Sign Up (New Account)

bash
curl -X POST https://public-api.tidy.com/api/v2/auth/signup \
  -H "Content-Type: application/json" \
  -d '{
    "first_name": "Jane",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

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.

Content

No source excerpt is available for this finding.

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 · references/rest-api-reference.md (reported line 171)May include surrounding context.

Example:

bash
curl -X POST https://public-api.tidy.com/api/v2/jobs \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -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 · references/rest-api-reference.md (reported line 226)May include surrounding context.

Example:

bash
curl -X POST https://public-api.tidy.com/api/v2/guest-reservations \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{