Back to skill

Security audit

Plant Doctor

Security checks for vulnerabilities and agentic risk

Overview

The core plant-care skill is coherent, but its optional dashboard design and privacy claims need review before users trust it with photos or shared account data.

Install the core skill only if you are comfortable with it storing plant details and care history under plants/ and, if memory is enabled, persisting that information across sessions. Treat the privacy and verification claims as marketing rather than proof. Do not deploy the optional dashboard for multiple users until the schema adds required owner fields, strict RLS policies, private storage rules, and tests that one user cannot access another user's plants or photos.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
dashboard-kit/DASHBOARD-SPEC.md:14
Finding

Dashboard SQL Schema Cannot Enforce Per-User Tenant Isolation

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
dashboard-kit/manifest.json:9
Finding

Dashboard Manifest Defines Nullable and Incomplete Record Ownership

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README instructs users to paste a setup prompt that will 'automatically configure your workspace' and describes creation of local state files, but it does not clearly warn that the skill may modify files in the user's environment. In an agent setting, vague setup instructions that trigger autonomous workspace changes increase the risk of unexpected file writes, prompt-driven misconfiguration, or broader unintended actions.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SECURITY.md (reported line 16)May include surrounding context.

md
## User Guidance for Secure Setup
To ensure your plant data remains private and secure:
- **File Permissions:** Ensure your OpenClaw workspace is private. Restrict access to the `plants/` directory so only your user account can read or write to it (e.g., `chmod 700`).
- **Dashboard Kit Warning:** If you choose to build the optional Dashboard Companion Kit, ensure your database (like Supabase) is configured securely with Row Level Security (RLS) so that only you can access your plant photos and schedules. Never upload your photos to a public storage bucket without authentication.
- **API Keys:** The dashboard requires a database connection. Never store your Supabase credentials or database URL in the `dashboard-kit` config files. Always use environment variables (`$SUPABASE_URL`, `$SUPABASE_SERVICE_ROLE_KEY`) and instruct the agent to use `process.env`.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SETUP-PROMPT.md (reported line 3)May include surrounding context.

md
Hi! I'd like to install the Plant Doctor skill. Please do the following:

1. Create a `plants/` directory in my workspace. Set permissions to 700 (`chmod 700 plants/`).
2. Create `plants/collection.json` containing an empty array `[]`. Set permissions to 600.
3. Create `plants/care-schedule.md` with a simple markdown table to track my watering and care reminders. Set permissions to 600.
4. If I have Supercharged Memory installed, please integrate my plant data so you remember my collection across sessions.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the agent to modify persistent local files (plants/collection.json and plants/care-schedule.md) when the user mentions watering, but it does not require explicit user consent, a notice that data will be stored, or confirmation before writing. This creates a state-changing side effect from ordinary conversation and can lead to silent persistence of personal data or unintended file modifications over time.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README makes a strong security and privacy guarantee ('never phones home' and 'no data exfiltration') without any substantiating code or verifiable evidence in the provided skill. Unverified safety claims can mislead users into granting trust and installing a skill that may later access networked tools or transmit data through the agent environment.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SECURITY.md (reported line 16)May include surrounding context.

md
## User Guidance for Secure Setup
To ensure your plant data remains private and secure:
- **File Permissions:** Ensure your OpenClaw workspace is private. Restrict access to the `plants/` directory so only your user account can read or write to it (e.g., `chmod 700`).
- **Dashboard Kit Warning:** If you choose to build the optional Dashboard Companion Kit, ensure your database (like Supabase) is configured securely with Row Level Security (RLS) so that only you can access your plant photos and schedules. Never upload your photos to a public storage bucket without authentication.
- **API Keys:** The dashboard requires a database connection. Never store your Supabase credentials or database URL in the `dashboard-kit` config files. Always use environment variables (`$SUPABASE_URL`, `$SUPABASE_SERVICE_ROLE_KEY`) and instruct the agent to use `process.env`.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill says it will proactively recalculate all watering schedules and notify the user when seasons change, which implies background regeneration of stored schedule data without an explicit warning that existing persisted records will be modified. Even within the plant-care context, silent bulk updates can surprise users, overwrite prior data, or create inaccurate schedules if assumptions are wrong.

Content

No source excerpt is available for this finding.