Back to skill

Security audit

Confluence

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Confluence integration skill, with disclosed read/write/delete capabilities and no hidden code or persistence in the artifact.

Before installing, verify the openclaw-morphixai plugin source, protect and rotate MORPHIXAI_API_KEY as needed, and connect a Confluence account with only the spaces and permissions required. Treat delete and update actions as real changes to Confluence content and confirm target page IDs before use.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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 (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:16
Finding

Unpinned Third-Party Plugin Installation

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 16
Vulnerability Type: Supply-chain risk from an unpinned third-party dependency
Risk Level: Medium

Vulnerable Code Snippet:

text
1. **Install plugin**: `openclaw plugins install openclaw-morphixai`

Technical Analysis

The installation instruction identifies the plugin only by package name. It does not pin a reviewed version or immutable digest, require signature or checksum verification, or document a trusted package source. Consequently, the code installed when a user follows this instruction may differ from the version that was originally reviewed.

The plugin implementation is not included in this project, so its executable behavior cannot be verified from the audited artifact. This does not establish that the current plugin is malicious; it creates a supply-chain exposure in which a compromised publisher account, package registry, dependency-resolution mechanism, or later plugin release could distribute altered code.

Attack Path

  1. An attacker compromises the plugin publisher, distribution registry, or mutable release channel for openclaw-morphixai.
  2. The attacker publishes a modified release under the expected package name.
  3. A user follows the documented unpinned installation command.
  4. The package manager resolves and installs the attacker-controlled release.
  5. When loaded or invoked, the modified plugin executes with the permissions available to the OpenClaw process.
  6. The plugin may access process-visible credentials, including MORPHIXAI_API_KEY, and misuse the Confluence capabilities granted to the connected account.

Impact Assessment

Successful exploitation could provide code execution within the security context of the OpenClaw process. The resulting scope depends on local sandboxing, filesystem permissions, environment-variable exposure, and the permissions of the connected Confluence account.

Potentia ...[truncated 359 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin openclaw-morphixai to a specifically reviewed version rather than resolving the latest mutable release.
  2. Where supported, pin an immutable artifact digest and verify a publisher signature or cryptographic checksum before installation.
  3. Document the authoritative registry and publisher identity to reduce dependency-confusion and typosquatting risks.
  4. Review the plugin source and transitive dependency lockfile before recommending installation.
  5. Run the plugin in a restricted environment with minimal filesystem, network, and process permissions.
  6. Grant the connected Confluence account only the spaces and operations required for the intended workflow.
  7. Keep MORPHIXAI_API_KEY scoped, short-lived where possible, excluded from logs, and subject to rotation and revocation.
  8. Establish an update-review process so version changes are assessed before deployment rather than installed automatically.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

该 Markdown 文件描述了 delete_page 删除页面的能力,但在相邻说明或注意事项中没有提示该操作会移除内容、可能不可逆,或建议用户在执行前确认目标页面。根据规则,Markdown 技能说明若涉及会影响用户数据或系统完整性的行为,应提供相应警示。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

整个技能说明均以中文撰写,未说明这是面向特定中文用户群体的限定,也没有提供语言/locale 选择。按规则,若技能强制特定语言而无用户选择或明确 justified 的区域性约束,属于自然语言层面的语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.