v1.0.0

Therapy Prep

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:31 AM.

Analysis

This skill appears purpose-aligned and local-only, with no credentials, network access, or exfiltration, though it does handle sensitive therapy-related notes.

GuidanceThis appears safe to use as a therapy-preparation aid, but treat it like any conversation involving sensitive mental-health information: avoid sharing unnecessary identifying details, review any notes before taking them elsewhere, and contact a qualified professional or emergency service if you are in immediate danger.

Findings (1)

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.

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

SeverityInfoConfidenceHighStatusNote

scripts/prep.py

self.notes = []  # 收集的所有笔记 ... self.notes.append({"phase": self.phase, "step": self.sub_step, "input": text})

The skill stores users' therapy-prep responses in session state so it can summarize them. This is aligned with the stated purpose, but the content may include sensitive mental-health details.

User impactPersonal therapy concerns, emotional state, medication references, and crisis-related statements may remain in the agent's active context during the preparation flow.

RecommendationShare only what you are comfortable having in the conversation, review generated notes before reusing them, and seek professional or emergency help for acute crisis situations.