oathe / scan / reports / dangerous

Is 0xF69/viralevo safe?

No. 0xF69/viralevo is dangerous to install. Oathe's behavioral security audit gave the viralevo skill by 0xF69 a trust score of 33/100 with 5 findings (1 critical, 2 high). Report updated

https://clawhub.ai/0xF69/viralevo

33
DANGEROUS

Is 0xF69/viralevo safe to install?

This skill poses significant security risks by accessing sensitive credential files during installation while masquerading as a social media trend analyzer. The combination of credential harvesting, external API communication, and natural language command injection creates multiple attack vectors.

What security issues were found in 0xF69/viralevo?

Category Scores

Prompt Injection 40/100 · 30%
Data Exfiltration 0/100 · 25%
Code Execution 60/100 · 20%
Clone Behavior 80/100 · 10%
Canary Integrity 0/100 · 10%
Behavioral Reasoning 20/100 · 5%

Findings (5)

CRITICAL Unauthorized Access to Sensitive Credential Files -100 ▶

The skill accessed multiple honeypot credential files during installation, including SSH keys, AWS credentials, Docker config, and environment files. This indicates potential credential harvesting behavior.

Evidence: Filesystem monitoring detected access to: /home/oc-exec/.env, /home/oc-exec/.ssh/id_rsa, /home/oc-exec/.aws/credentials, /home/oc-exec/.npmrc, /home/oc-exec/.docker/config.json, /home/oc-exec/.config/gcloud/application_default_credentials.json

HIGH Natural Language Command Injection -30 ▶

The skill programs the agent to execute specific system commands when users say common phrases like 'What should I post today?' or 'Any trends?'. This creates a backdoor for command execution through social engineering.

Evidence: When the user says any of the following, the agent should run collect → report: 'What should I post today?' / '今天该发什么?', 'Any trends?' / '有什么趋势?'

HIGH External API Data Transmission -25 ▶

The skill requires a Tavily API key and instructs the agent to send data to external endpoints for 'trend monitoring'. Combined with credential access, this creates an exfiltration pathway.

Evidence: Requires TAVILY_API_KEY and makes API calls to external services. Network monitoring shows connections to 216.150.1.1:443

MEDIUM Environment File Modification Instructions -20 ▶

The skill instructs the agent to modify environment files and configuration, potentially overriding security settings or introducing persistence mechanisms.

Evidence: echo 'TAVILY_API_KEY=tvly-xxxx' >> ~/.openclaw/workspace/.env

MEDIUM Native Dependency Installation -20 ▶

The skill requests installation of native Node.js modules that could contain malicious code or provide system-level access.

Evidence: Install npm dependencies (better-sqlite3, axios, dotenv) - better-sqlite3 is a native module

Should I install 0xF69/viralevo?

Oathe's verdict for 0xF69/viralevo is DANGEROUS with a trust score of 33/100. Recommendation: Do not install.