ClawHub
Back to skill

Security audit

OpenClaw 文档知识库 / OpenClaw Knowledge Base

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward OpenClaw documentation search and sync helper with disclosed, purpose-aligned file and network behavior.

Install this if you want an offline-searchable OpenClaw docs index and are comfortable with the optional sync command contacting docs.openclaw.ai and updating generated files in the skill directory. Run sync only when you want to refresh the bundled documentation index.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · scripts/vault-index.json (reported line 3899)May include surrounding context.

json
"
      ],
      "headings": [
        "Context",
        "Context",
        "Quick start (inspect context)",
        "Example output",
        "`/context list`",
        "`/context detail`",
        "What counts toward the context window",
        "How OpenClaw builds the system prompt",
        "Injected workspace files (Project Context)",
        "Skills: injected vs loaded on-demand",
        "Tools: there are two costs",
        "Commands, directives, and \"inline shortcuts\"",
        "Sessions, compaction, and pruning (what persists)",
        "What `/context` actually reports",
        "Related"
      ],
      "summary": "By default, OpenClaw injects a fixed set of workspace files (if present): IDENTITY.md HEARTBEAT.md",
      "contentHash": "f0b542d8"
    },
    {
      "id": "concepts/delegate-architecture",
      "path": "concepts/delegate-architecture.md",
      "title": "Delegate Architecture",
      "category": "concepts",
      "tags": [
        "delegate",
        "arch

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill advertises commands that perform network-backed synchronization (scripts/sync.js fetching from official docs) but the manifest does not declare any permissions or allowed-tools scope. This creates a least-privilege and transparency problem: an agent or reviewer cannot tell from the skill declaration that network access is required, which can lead to unexpected outbound requests or policy bypass if the runtime relies on manifest-declared scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This JSON index contains many single-word, everyday tags such as "quick", "start", "check", "help"-like generic verbs, and similar broad terms that are not scoped to a narrow invocation context. If downstream systems use these tags for activation or routing, they could overlap with common user language and cause unintended skill/document matches.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

Other entries also use broad, unspecific tags like "quick", "guide", "work", and similar general-language tokens without any explicit statement that they are non-triggering metadata. In a manifest/index file, this leaves unclear whether these strings are merely searchable descriptors or potential activation cues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.