Deep Dialogue
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is an instruction-only conversation framework with no code, credentials, or system access; users should only note that it gives mental-health-adjacent dialogue guidance and documents an unpinned Git clone install path.
This skill appears safe to install from the reviewed artifacts. Before using it, remember that it is a reflective conversation framework, not therapy or crisis support, and review the exact source if installing via the README's Git clone command.
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 ask deep personal questions and offer psychological framing that could feel authoritative.
The skill is explicitly designed for sensitive philosophical and psychological conversations. This is its disclosed purpose, but users may place extra trust in agent-generated psychological interpretations.
Use when exploring personal issues, existential questions, meaning-making, belief examination, or psychological patterns.
Use it for reflection, not as a substitute for licensed mental health care, and avoid relying on it for crisis or clinical decisions.
If a user installs from the live repository later, they may receive content that was not part of this review.
The README documents installing from a remote Git repository without pinning a commit. This is common and no automatic execution is shown, but future repository contents may differ from the reviewed artifacts.
git clone https://github.com/arikmir/deep-dialogue.git ~/.claude/skills/deep-dialogue
Install from a trusted source and consider pinning or reviewing the exact commit before use.