ClawHub
Back to skill

Security audit

Agent Task Status

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local audit helper that reads OpenClaw agent transcripts to summarize assignment and report status.

Install only if you are comfortable letting the skill inspect local OpenClaw agent session transcripts. Prefer explicit --agents and --base values, use --tail when a full transcript scan is unnecessary, and write --output-file only to a location appropriate for potentially sensitive assignment/report excerpts.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill instructs users to run a local Python script that inspects agent session indexes and transcript files, implying file reads, environment-dependent path resolution, and optional file output, yet the manifest declares no explicit tool scope or permissions. This creates an authorization/visibility gap: downstream systems or reviewers cannot tell from the skill header that it accesses potentially sensitive transcript data and writes results to disk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file defines default field labels in Chinese and later uses a Chinese assignment keyword by default, which creates a language-specific behavior without explicit user opt-in. This is a natural-language policy concern because the skill defaults to a specific locale rather than presenting a neutral default or prompting for language selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default value for --assign-keyword is the Chinese phrase "正式任务分配：", which means the script assumes a specific language and transcript format unless the user overrides it. Because the file does not document a region-specific justification or require opt-in, this is a language/locale policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The description includes only Chinese example requests for invoking the skill's use cases, which may imply a language-specific interaction pattern without explicitly offering user language choice. The file does not state that other languages are equally supported or that Chinese is optional.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.