fragments
PendingVirusTotal audit pending.
Overview
No VirusTotal analysis has been recorded yet. File reputation checks will appear here once the artifact hash has been scanned.
Findings (0)
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.
Anyone or any agent process with access to the configured token may be able to read or change Memos data according to that token's permissions.
The skill needs a Memos PAT to authenticate MCP access. This is expected for the integration, but it grants account-level access to the user's Memos data and is not declared in the registry credential metadata.
Ask the user for their Memos Personal Access Token (format: `memos_pat_*`).
Use the least-privileged token available, keep config files private, avoid committing MCP config files containing tokens, and revoke the token if the skill is no longer used.
If the user confirms the wrong operation, memos, comments, or daily-log content could be changed or deleted.
The skill can perform high-impact Memos mutations, including update and irreversible delete, but the artifacts require user confirmation before write calls.
Create, search, update, delete, and comment on memos via MCP tools. ... Write operations require user confirmation before calling.
Review previews, diffs, memo IDs, and deletion warnings carefully before approving any write or delete action.
After installation, the agent may prompt for daily-log updates at the end of sessions and may fetch today's log as part of that workflow.
The optional plugin persists as an idle-session hook that injects a prompt for daily-log capture after meaningful work. This is disclosed and does not save without confirmation, but it changes ongoing agent behavior.
"session.idle": async ... "You completed a task. Follow the fragments skill daily-log hook workflow"
Install the hook only if passive daily-log prompting is desired, prefer project-level installation where possible, and disable/remove the hook if the prompts are not wanted.
Sensitive details from an agent session could become persistent and visible to the Memos workspace if the user approves the merged log.
The daily-log feature stores session summaries as persistent Memos content, and the artifact states daily logs are workspace-visible. User confirmation is required before saving.
Summarize this session's work as `.plan` lines ... Show the user the full merged log ... Save ... Visibility is always PROTECTED (workspace-visible).
Review daily-log entries before saving, remove secrets or sensitive client/project details, and understand who can see PROTECTED Memos content in the workspace.