Soulcraft Identity

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This instruction-only skill coherently helps create agent identity files, with no code, install steps, credentials, or external data access shown.

This appears safe to install as an instruction-only skill. When using it, provide only the context needed, and review the generated SOUL.md so it does not encode unsafe triggers, overbroad autonomy, or unwanted communication patterns.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

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.

#
ASI06: Memory and Context Poisoning
Low
What this means

A generated identity file could strongly influence how an agent communicates, decides, and responds to triggers in later use.

Why it was flagged

The generated SOUL.md is a reusable instruction artifact that can shape future agent behavior. This is the disclosed purpose of the skill, but it should be reviewed because persistent instructions can be over-trusted if poorly written.

Skill content
Creates a comprehensive SOUL.md file that defines an agent's: ... Core operating principles ... Decision boundaries ... Safety guardrails ... Triggered workflows
Recommendation

Review the generated SOUL.md carefully, especially decision boundaries, safety rules, and triggered workflows, before using it as persistent agent guidance.