list-running-starred-services

• Outcome: Review
• Latest audit: May 29, 2026, 9:29 PM
• Version:
  1.0.1

Overview

The skill appears to run an internal service-listing CLI and print raw results, which fits its purpose but should be reviewed because it can run implicitly and expose operational metadata.

Install only if you are comfortable with the agent using your existing `bytedcli` access to list starred TCE services. Prefer invoking it explicitly, and review the output for internal service metadata before sharing it outside your organization.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill enables implicit invocation without any constrained trigger description, which increases the chance the agent will call it opportunistically in unrelated contexts. Because the skill is explicitly designed to run a CLI command and return raw output, accidental invocation can disclose service metadata or internal operational details without clear user intent.

Ssd 3

Medium

• Confidence: 97% confidence
• Finding: The skill description and default prompt explicitly instruct the agent to print the original raw output from 'bytedcli tce list-starred-service' directly. Raw CLI output may contain sensitive service names, identifiers, internal endpoints, ownership metadata, or other operational data, and the lack of filtering or minimization makes disclosure more dangerous in this context.

VirusTotal

61/61 vendors flagged this skill as clean.