Back to skill

Security audit

clawlite-ceo-review

Security checks for vulnerabilities and agentic risk

Overview

This is a strategy-review skill that reads local project context and gives structured planning feedback, with no hidden code execution, persistence, or exfiltration behavior found.

Install this if you want a Chinese-language strategic planning reviewer that may inspect your current repository history, diffs, TODOs, and design docs before giving feedback. Avoid using it in repositories containing sensitive material unless you are comfortable with those local files being read for context.

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
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest-style description is presented only in Chinese, Japanese, Korean, and Spanish, with no English or explicit user language selection. This imposes locale-specific behavior/content without opt-in, which matches the policy category for language or locale violations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.