Self-Guardian
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The provided artifacts show an instruction-only safety guardrail that adds confirmations around risky file and shell actions without code, credentials, or external access.
This appears to be a benign safety skill. Before installing, understand that it is designed to slow down or block risky file and shell operations unless you provide explicit confirmation.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may pause, ask for confirmation, or avoid sensitive operations even when a task seems routine.
The skill intentionally imposes broad behavioral constraints on future file and shell operations. This can change how the agent responds to user requests, but it is clearly disclosed and matches the safety purpose.
These rules are NON-NEGOTIABLE safety constraints. Follow them for EVERY file or shell operation
Install if you want extra safeguards around destructive operations, and expect additional confirmation prompts for risky file or shell actions.