v1.0.0

Bootstrap

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 6:32 AM.

Analysis

This instruction-only onboarding skill is coherent and purpose-aligned, but it creates a persistent local SOUL.md profile containing personal preferences and future behavior guidance.

GuidanceThis skill appears safe to use if you want a persistent AI identity file. Before saving, read the generated SOUL.md carefully, remove anything too personal, and make sure the autonomy and future-learning language matches how much initiative you want the AI to take.

Findings (3)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityInfoConfidenceHighStatusNote

SKILL.md

Save to `./memory/SOUL.md`:
   - `mkdir -p ./memory`
   - Write the confirmed SOUL.md

The skill instructs the agent to create a local directory and write a file. This is scoped, disclosed, and happens after confirmation, so it is a normal part of the skill rather than a concern.

User impactInstalling and using the skill may create or update a local memory file that future sessions can use.

RecommendationReview the final SOUL.md before confirming, especially if an existing file will be overwritten or merged.

Rogue Agents

SeverityLowConfidenceMediumStatusNote

templates/SOUL.template.md

Over time, anticipate needs and act on [User Name]'s behalf with increasing accuracy. Early stage: proactively ask casual/personal questions after tasks

The template gives the future AI proactive and autonomy-oriented behavior guidance. This is visible in the generated file and aligned with personalization, but users should ensure it matches their intended boundaries.

User impactThe saved profile may encourage the AI to be more proactive and to ask personal follow-up questions in future interactions.

RecommendationBefore confirming, adjust the Growth section or autonomy wording if you want the AI to ask permission more often or avoid personal follow-up questions.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

templates/SOUL.template.md

Learn [User Name] through every conversation — thinking patterns, preferences, blind spots, aspirations.

The generated SOUL.md is designed to preserve and reuse a personal model of the user. That is central to the skill’s purpose, but it can include sensitive personal preferences or self-described weaknesses.

User impactPersonal details provided during onboarding may become persistent context for future AI behavior.

RecommendationDo not include secrets or highly sensitive personal details unless you are comfortable storing them in ./memory/SOUL.md; edit the file before saving if needed.