Self Learning Agent
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a transparent local memory-card workflow, but it can automatically save and reuse personal, project, and infrastructure details across sessions.
This skill appears coherent and instruction-only. Install it if you want a local persistent memory workflow, but treat the memory directory like sensitive notes: review it, keep it out of public repositories, and do not store secrets or private details unless you are comfortable with future agent sessions seeing them.
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 remember and later rely on details you did not explicitly ask it to save, including sensitive project or personal context.
The skill intentionally creates persistent memory that may store personal, project, or infrastructure facts without a separate prompt each time. This is aligned with the memory purpose, but retained or inaccurate cards could be reused in later sessions.
"Automatic (agent should capture without being asked)" ... "User corrections" ... "Non-obvious facts about infrastructure, people, or projects"
Use this only in trusted workspaces, review cards and logs periodically, and avoid saving passwords, tokens, private personal data, or sensitive infrastructure details unless you intentionally want them retained.