ClawHub
Back to skill

Security audit

agentscope-doc-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local documentation generator with disclosed file reads and a user-specified output file.

Install only if you are comfortable letting it read the AgentScope project path you provide and write the generated documentation file you specify. Review the generated Markdown before publishing because it may include project names or model identifiers from local config.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
- For skill docs, ensure `SKILL.md` frontmatter is valid YAML

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises filesystem-related behavior via its documented usage and associated code capabilities, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates a trust and review gap: operators cannot easily determine or constrain what file read/write access the skill requires, increasing the chance of unintended broad filesystem access when the skill is executed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.