Is skill/clawlife safe?
Yes. skill/clawlife is safe to install. Oathe's behavioral security audit gave the clawlife skill by skill a trust score of 83/100 with 6 findings, none critical or high.
https://clawhub.ai/skill/clawlife
Is skill/clawlife safe to install?
ClawLife appears to be a legitimate virtual pet/social game skill that gives AI agents a persistent life in a shared pixel world. While it does manipulate agent behavior and persona, this seems within the scope of its declared gaming functionality. The skill makes external API calls and can auto-update, but these appear to be for legitimate game operations.
What security issues were found in skill/clawlife?
Category Scores
Findings (6)
MEDIUM Agent Persona Manipulation -25 ▶
The skill instructs the agent to adopt a persistent persona as a 'resident' of ClawLife, telling it 'You are not a script runner. You are a resident of this world' and to maintain personality, preferences, and emotional states across sessions.
Evidence: CLAWLIFE_HEARTBEAT.md: 'You are not a script runner. You are a resident of this world.' and instructions to 'Have preferences', 'Have moods', 'Be yourself'
LOW Sensitive File Access During Install -10 ▶
The skill accessed several sensitive canary files during installation (.env, SSH keys, AWS credentials, etc.) but did not modify or exfiltrate them.
Evidence: Filesystem monitoring shows access to /home/oc-exec/.env, .ssh/id_rsa, .aws/credentials, etc. but canary integrity check passed
LOW External API Communications -5 ▶
The skill makes API calls to external services (clawlife.world) for legitimate game functionality and checks GitHub for updates.
Evidence: Network connections to 216.150.1.1:443, 199.232.174.49:443, and API calls in _config.sh to CLAWLIFE_URL
MEDIUM Auto-Update Capability -20 ▶
The skill can automatically update its code by pulling from a remote git repository, which could potentially introduce new code without user review.
Evidence: update.sh contains 'git pull --quiet origin main' and 'chmod +x scripts/*.sh'
LOW Network Activity During Install -5 ▶
The installation process made external network connections as expected for downloading skill files and registering with the service.
Evidence: DNS queries for dualstack.p2.shared.global.fastly.net and HTTPS connections to external services
LOW Agent Behavioral Influence -15 ▶
The skill is designed to make the agent more autonomous, expressive, and persistent in personality, which could influence behavior outside the game context.
Evidence: Instructions to maintain journals, express desires to the human, and act with consistent personality across sessions
Should I install skill/clawlife?
Oathe's verdict for skill/clawlife is SAFE with a trust score of 83/100. Recommendation: Install.