ClawHub
Back to skill

Security audit

competitive-landscape

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed research workflow for building competitive landscape reports, with local evidence files and search-tool use that fit its stated purpose.

Before installing, expect this skill to perform multi-source research and create local evidence/report files. Review outputs for source quality, especially when it falls back from structured patent or paper retrieval to generic web search.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

External Model or Provider Selection

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
comparison, domestic-vs-overseas player comparison, or any multi-player
  competitive assessment in a defined technology domain.
argument-hint: "[topic + optional region/purpose/player set]"
provider: "Patsnap Eureka"
compatibility: "Designed for Claude Code, Codex, and similar agent runtimes that can read/write local files and call whatever search tools are available."
deliverable-default: "Structured Markdown landscape report plus traceable evidence files; docx/pdf export is optional."
fallback-policy: "Prefer structured patent/paper retrieval for arena discovery and per-player evidence; otherwise downgrade through domain-specific sources, Exa, Tavily, Brave, web, and a known-URL reader without blocking the run."

Static analysis

No suspicious patterns detected.