ClawHub
Back to skill

Security audit

geo-brand-mentions

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent brand-visibility reporting workflow, but it asks the agent to run an undeclared local shell command as authoritative evidence.

Review the `seogeo brand-scan` requirement before installing. Only use this skill in an environment where that command is trusted and expected, and be aware it will create a `GEO-BRAND-MENTIONS.md` report in the workspace.

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

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill instructs execution of an external seogeo brand-scan shell command as a 'ground truth' source, but the command is not declared or constrained by the manifest and may invoke arbitrary local binaries or scripts present in the environment. Treating its output as authoritative creates a trust boundary violation: a malicious or tampered executable could exfiltrate data, execute unintended actions, or return manipulated results during analysis.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill's stated purpose is passive platform scanning, yet it includes shell execution through Bash without a clear necessity tied to that purpose. This expands the capability surface from reading/searching to local code execution, which is dangerous in agent environments because it can trigger side effects, consume local secrets, or run attacker-controlled tooling under the guise of normal analysis.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown skill description explicitly instructs the agent to generate a file called GEO-BRAND-MENTIONS.md, which is a user-data-affecting write operation. The document does not include any warning or disclosure that running the skill will create or modify files in the user's workspace.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.