Multi-Chat Context Manager
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears to be a coherent local context-store CLI; the main cautions are plaintext conversation storage and an all-context clear operation.
This looks safe to use for a local manual context store. Before installing, make sure you are comfortable with conversation history being saved in plaintext under the skill's data directory, avoid storing secrets, and be careful with the clear command because it can delete all stored contexts if run without a channel.
Findings (2)
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.
Messages and responses stored with this tool may remain on disk and be retrievable later by anyone or any workflow with access to the skill files.
The skill intentionally persists conversation messages and responses as local plaintext JSON, which is expected for its purpose but can expose private conversation content or reuse stale/untrusted context.
Contexts are saved as JSON, keyed by channel/user/thread IDs... Stores data in plaintext JSON (not encrypted)
Avoid storing secrets or sensitive personal data, restrict local file access, and clear contexts when they are no longer needed.
An accidental or overly broad clear command could remove all conversation context stored by this skill.
The clear command deletes all stored contexts when called without a channel ID. This is confined to the skill's own context store, but an unintended invocation could erase saved context.
def clear_context(channel_id=None, user_id=None, thread_id=None): ... if channel_id is None: contexts.clear()
Use channel/user/thread arguments for targeted clearing, and require explicit user confirmation before running a clear-all operation.