ClawHub
Back to skill

Security audit

Geo Deep Imitate

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says, but it stores a GEO API key in a local plaintext file and sends task content to the GEO service.

Install only if you trust ai.gaobobo.cn with your GEO API key, fetched reference content, and task metadata. Consider storing the key with restrictive permissions, removing ~/.qclaw/geo-api-key when no longer needed, and reviewing exported files under ~/.qclaw/geo-exports.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to read secrets from local home-directory files and to persist a user-provided GEO API key there, even though the manifest only declares a web_fetch tool requirement. This expands the skill's effective privilege boundary to local credential access and storage, creating a risk of unauthorized secret handling, accidental disclosure, and misuse of credentials in later network requests.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The manifest presents the skill as a web_fetch-based content-fetching capability, but the body directs multiple direct remote API operations for key verification, article generation, polling, export, and reporting. This mismatch can mislead reviewers and users about the skill's actual behavior and trust boundary, increasing the chance that sensitive data and credentials are transmitted without appropriate scrutiny.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill tells the user to save an API key to a local file using a simple shell redirection, without warning about credential persistence, file permissions, multi-user access, shell history, or safer storage alternatives. This can expose long-lived credentials to other local processes or users and normalizes insecure secret-handling practices.

Static analysis

No suspicious patterns detected.