Back to skill

Security audit

Open Plantbook

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly scoped Open Plantbook API helper that uses expected credentials and network calls for plant lookup and user-plant writes.

Install this only if you intend to let the agent use Open Plantbook credentials and make authenticated requests to open.plantbook.io. Use OAuth credentials only for workflows where you want user-plant writes or sensor uploads, review delete/update requests before approving them, and avoid placing unrelated secrets in the optional env file.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (9)

Tainted flow: 'request' from os.getenv (line 122, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/openplantbook_cli.py (reported line 133)May include surrounding context.

python
},
    )
    try:
        with urlopen(request, timeout=30) as response:
            status = response.status
            payload = response.read().decode("utf-8")
    except HTTPError as exc:

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 · SKILL.md (reported line 95)May include surrounding context.

md
- `GET /api/v1/plant/detail/{pid}/`
- `POST /api/v1/plant/create`
- `PATCH /api/v1/plant/update`
- `DELETE /api/v1/plant/delete`

Always re-check `/api/schema/` before using these for writes or when field details matter.

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 · SKILL.md (reported line 227)May include surrounding context.

md
- `GET /api/v1/plant/detail/{pid}/`
- `POST /api/v1/plant/create`
- `PATCH /api/v1/plant/update`
- `DELETE /api/v1/plant/delete`

Always re-check `/api/schema/` before using these for writes or when field details matter.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/publish-notes.md (reported line 97)May include surrounding context.

CREDENTIAL_PATTERN='client_secret|OPENPLANTBOOK_API_KEY|OPENPLANTBOOK_OAUTH_CREDENTIALS|token' rg -n "$PLATFORM_PATTERN" plugins/openplantbook/skills/openplantbook skills/openplantbook -g '!**/references/publish-notes.md' rg -n "$CREDENTIAL_PATTERN" plugins/openplantbook/skills/openplantbook skills/openplantbook find plugins/openplantbook/skills/openplantbook -name 'pycache' -o -name '.pyc' -o -name '.env' -o -name '.env'

text

The `find` command should produce no output. The `rg` commands may show documented metadata, placeholders, and env-var names; investigate anything that looks like a local filesystem path, platform-specific config path, or literal secret value.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill documentation clearly instructs the agent to read environment variables, optionally read an env file from disk, and make authenticated network requests, but the manifest declares no explicit tool scope such as permissions or allowed-tools. That mismatch can cause the platform or reviewer to underestimate the skill's access to secrets, files, and external write-capable APIs, increasing the chance of unsafe deployment or overbroad execution.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description presents the skill as plant search/detail and user-plant writes, but later documentation also enables sensor-data instance registration and upload workflows. Undisclosed write/integration capabilities can mislead users and security reviewers about the true action surface, especially because these flows send authenticated telemetry to an external service.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/publish-notes.md (reported line 115)May include surrounding context.

Expected file list:

text
plugins/openplantbook/skills/openplantbook/SKILL.md
plugins/openplantbook/skills/openplantbook/agents/openai.yaml
plugins/openplantbook/skills/openplantbook/references/publish-notes.md
plugins/openplantbook/skills/openplantbook/scripts/openplantbook_cli.py

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The section introduces the bundled helper CLI as supporting quick workflows, then states it supports only search/detail and create, while directing update/delete to direct HTTP instead. This does not affect runtime safety directly, but it creates intent/documentation inconsistency about what the packaged helper actually covers versus the broader skill workflows described elsewhere.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
0% confidence
Finding

This file is a Python code file, so SQP-1 does not apply. For SQP-2, the network calls and credential use are clearly part of the stated purpose in the module docstring and CLI help, and the file contains user-facing descriptions of those actions. For SQP-3, the optional --lang argument does not force a specific language or locale, so there is no policy violation.

Content

No source excerpt is available for this finding.