ClawHub
Back to skill

Security audit

BadgerPeek

Security checks across malware telemetry and agentic risk

Overview

BadgerPeek is a narrowly scoped, read-only Honeybadger inspection skill that uses a user-provided token to fetch project and error data without hidden persistence or mutation behavior.

Install only if you are comfortable letting the agent read Honeybadger project names, error details, context, and stack traces available to the supplied token. Prefer a least-privilege Honeybadger token and avoid pasting unnecessary returned fields into chats or logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
auth_file=$(mktemp)
  response_file=$(mktemp)
  chmod 600 "$auth_file" "$response_file"
  printf 'user = "%s:"\n' "$token" >"$auth_file"

  if ! status=$(curl \
Confidence
80% confidence
Finding
chmod 600

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.