bls-skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Baidu Log Service query helper that uses expected Baidu credentials and endpoints, with sensitive-log handling risks users should manage.

Install only if you want your agent to query Baidu Log Service. Use least-privilege, preferably read-only BLS credentials; avoid passing secret keys on the command line when possible; and confirm region, project/logstore, query, and time window before running broad searches because returned logs may contain secrets or personal data.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger keywords include broad phrases such as '日志服务', '日志查询', and '检索日志', which can cause the skill to activate for general logging-related conversations rather than explicit BLS requests. In this skill's context, accidental activation is more dangerous because the skill can access credentials and perform authenticated log queries, potentially exposing sensitive operational data when the user did not intend to invoke it.

VirusTotal

1/64 vendors flagged this skill as malicious, and 63/64 flagged it as clean.

View on VirusTotal