Enhanced Memory

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent local memory organizer with no credential or network behavior, but it intentionally keeps and searches personal memory for a long time.

This skill appears safe for its stated purpose if you want a local, structured memory system. Before installing, decide whether you are comfortable with permanent agent memory, avoid storing passwords or secrets in memory files, periodically review what has been saved, and only enable the optional cron job if you want automatic maintenance.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

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.

#
ASI06: Memory and Context Poisoning
Medium
What this means

Personal details saved in memory may be surfaced in future agent sessions, and inaccurate or maliciously edited memory entries could influence later responses.

Why it was flagged

The skill intentionally stores and retrieves personal context across time, including sensitive life categories, and keeps archived memory indefinitely.

Skill content
organized, searchable, long-lived memory ... relationship context ... food logs ... training ... Active → archive, never delete
Recommendation

Use this only for information you are comfortable keeping in agent memory; review memory files periodically, avoid storing secrets, and consider adding a manual deletion or retention policy.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

Running the maintenance script can change which memories are considered active, although the artifacts show it archives rather than destroys the data.

Why it was flagged

The lifecycle manager mutates local memory files by copying old Markdown files to an archive and removing them from active memory directories.

Skill content
shutil.copy2(file_path, target_path)

    # 从当前目录删除文件
    file_path.unlink()
Recommendation

Run the lifecycle script only when you intend to reorganize memory, and back up important memory files if active/archive placement matters.

#
ASI10: Rogue Agents
Low
What this means

If the user enables cron, memory files may be reorganized automatically without a fresh prompt each month.

Why it was flagged

The skill documents an optional cron job that keeps memory maintenance running on a schedule.

Skill content
Set up monthly auto-archival:

# Run on the 1st of every month at 03:00
0 3 1 * * cd /path/to/workspace && python3 scripts/memory_lifecycle_manager.py
Recommendation

Only add the cron job if you want unattended memory maintenance, and remove it if you prefer manual control.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

Users have less provenance information to rely on when deciding whether to trust the included memory-management scripts.

Why it was flagged

The skill has limited external provenance metadata, although the provided scripts are present, use no external dependencies, and the static scan reported no suspicious patterns.

Skill content
Source: unknown
Homepage: none
No install spec — this is an instruction-only skill.
Recommendation

Review the included scripts before installing and prefer a known repository or signed source when available.