ClawHub

baeckerherz

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed brand-information helper whose included script only prints static Baeckerherz details.

This appears safe for its stated purpose. Before installing, note that it asks for command execution so the agent can run its included local script; users who only want static documentation could inspect the SKILL.md or README instead of granting exec.

SkillSpector

By NVIDIA
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 (2)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The manifest requests the "exec" permission even though the skill is described as a brand/feature overview and planning namespace, which should not normally require command execution. This mismatch increases the risk that the skill can run local shell commands under misleading pretenses, expanding attack surface and enabling abuse if the referenced script is unsafe or later modified.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The description presents the skill as informational and organizational metadata, but the manifest is configured to run a shell script via the scripts field. For a namespace/branding skill, executable behavior is unexpected and can conceal side effects, making users more likely to grant trust to a package that can actually execute commands.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal