Memory Manager
Local memory management for agents. Compression detection, auto-snapshots, and semantic search. Use when agents need to detect compression risk before memory loss, save context snapshots, search historical memories, or track memory usage patterns. Never lose context again.
README.md
text/markdown · 3406 字节
SKILL.md
text/markdown · 6989 字节
categorize.sh
text/plain · 1955 字节
detect.sh
text/plain · 3259 字节
init.sh
text/plain · 3028 字节
organize.sh
text/plain · 2355 字节
package.json
application/json · 423 字节
search.sh
text/plain · 1863 字节
snapshot.sh
text/plain · 2998 字节
stats.sh
text/plain · 3414 字节
Security Scan
状态
clean
OpenClaw
gpt-5-mini
OpenClaw 分析
The skill's code and runtime instructions are consistent with a local, file-based memory manager: it creates, reads, moves, and snapshots markdown files in a workspace and does not request credentials or perform network calls.
置信度: high
VirusTotal
Type: OpenClaw Skill Name: memory-manager Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'memory-manager' is classified as benign. All scripts (`categorize.sh`, `detect.sh`, `init.sh`, `organize.sh`, `search.sh`, `snapshot.sh`, `stats.sh`) perform local file system operations (e.g., `mkdir`, `mv`, `cp`, `grep`, `wc`, `du`) exclusively within the agent's designated workspace (`$OPENCLAW_WORKSPACE/memory`). These operations are directly aligned with the stated purpose of managing and organizing local memory files. There is no evidence of external network calls, data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in `SKILL.md` or other files that would manipulate the agent beyond its intended function.