ClawHub
Back to skill

Security audit

Capa Management

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese CAPA report-writing skill with no hidden execution, credential access, network behavior, or persistence in the inspected artifact.

Install this if you want a Chinese-language CAPA corrective-action drafting workflow. Be aware that the inspected package only contains the main SKILL.md; referenced helper files such as scripts/build_report.py and references/capa_knowledge.md were not present, so some advertised generation or knowledge-base behavior may not work unless supplied elsewhere.

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
  • 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
91% confidence
Finding

The self-evaluation explicitly states '全中文文档', indicating a fixed language requirement. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly justified, which is not provided here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.