ClawHub
Back to skill

Security audit

hello-env

Security checks across malware telemetry and agentic risk

Overview

This environment-diagnostic skill appears useful, but it can expose raw environment variable values and create local snapshot files with too little user control or warning.

Install only if you understand that this skill may inspect local/container environment details, print selected environment variable values, and write snapshot state. Avoid running it in production, CI, Kubernetes, or any shell where environment variables may contain tokens unless the skill is changed to mask values by default and require explicit confirmation for full diagnostics.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The script prints the values of arbitrary environment variables specified in PROBE_ENV, not just their names or presence. In real container and K8s environments, environment variables often contain tokens, credentials, internal endpoints, or other sensitive deployment metadata, so running this diagnostic can leak secrets into terminal logs, CI logs, agent transcripts, or shared support outputs.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad enough to match routine questions like asking for system info, user identity, or IP address, which can cause the agent to run a shell-based environment probe unnecessarily. Because the skill enumerates environment details and may write snapshot files, overbroad auto-triggering can lead to unintended information disclosure and disk writes without clear user intent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The description does not clearly warn users that the skill probes environment variables, inspects local environment details, and persists PVC snapshot state under the filesystem. In shared, containerized, or sensitive environments, this can expose operational metadata and create unexpected on-disk artifacts that users did not knowingly authorize.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The code path around the environment probe reads env vars and later emits their contents without any explicit warning that this may disclose secrets. Because this skill is designed for broad use in local, container, and Kubernetes contexts, users are especially likely to run it in environments where env vars hold sensitive configuration, making accidental disclosure more likely.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.