Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent local personal-memory skill, but users should be careful because it can persist submitted content in local memory and vector stores.
Install only if you intend to use a local PKM memory system. Treat anything saved through it as persistent, avoid storing secrets or sensitive personal data unless you trust the local PKM/Qdrant services, and prefer explicit confirmation before adding new memories.
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
# 存储记忆（异步）
curl -X POST http://127.0.0.1:8001/ingest \
-H "Content-Type: application/json" \
-d '{"text":"记忆内容","role":"user"}'
The trigger phrase "记忆" is extremely broad and likely to appear in ordinary user conversation, which can cause the skill to activate unintentionally. In this skill, accidental activation is more dangerous because it can route user content into persistent memory storage and retrieval workflows without clear user intent.
The skill describes storing and retrieving memory through local HTTP services and Qdrant, but it does not warn users that submitted content may be transmitted to local services and stored persistently. This creates a privacy and consent risk because users may disclose sensitive data without understanding that it will be retained across sessions or indexed in multiple backends.
The skill instructs sending user-provided memory content over HTTP to a local ingestion service at 127.0.0.1:8001. Even though the endpoint is local, this is still external transmission from the agent context into another service, and in this skill it directly handles potentially sensitive user data for persistent storage without any authentication, consent, or transport-security discussion.
# 存储记忆（异步）
curl -X POST http://127.0.0.1:8001/ingest \
-H "Content-Type: application/json" \
-d '{"text":"记忆内容","role":"user"}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s http://localhost:7334/collections | python3 -c "import sys,json; d=json.load(sys.stdin)['result']; [print(c['name']) for c in d['collections']]"
curl -s http://localhost:7334/collections//points/count
### 语义搜索
The natural-language instructions and usage guidance are presented exclusively in Chinese, which can amount to a language policy issue if the skill is intended for a broader audience and does not obtain user opt-in. There is no indication that the locale restriction is optional or justified as region-specific.
No suspicious patterns detected.