Jasper Recall

Local retrieval-augmented generation system for AI agents to index, search, and recall private, shared, and learned memories using ChromaDB and SkillBoss emb...

Things to check before installing: 1) Source trust: The package includes many scripts that will write to your home (~/.openclaw, ~/.jasper-recall, ~/.local/bin) and modify OpenClaw config; only install if you trust the publisher or have reviewed all files (especially scripts/recall.py, scripts/sync-shared.py, and any code that makes network requests). 2) Embeddings / network: SKILL.md indicates embeddings route through SkillBoss API Hub and requires SKILLBOSS_API_KEY. That means text chunks may be sent off-host for embedding — if you will index private or sensitive content, confirm the embedding provider, data handling, and whether you want to expose that content. 3) OpenClaw changes: setup will attempt to add and enable a jasper-recall plugin in ~/.openclaw/openclaw.json (autoRecall:true). Back up openclaw.json before running setup and review the change — auto-enabling a plugin can change agent behavior. 4) Server exposure: the bundled server defaults to host=127.0.0.1 (safer) and public_only=true. Avoid starting it bound to 0.0.0.0 or enabling RECALL_ALLOW_PRIVATE unless you intentionally want remote/private access. CORS is set to '*', so if you bind to an external interface, web origins can query it. 5) Credentials mismatch: registry metadata shows no required env vars but SKILL.md lists SKILLBOSS_API_KEY. Ask the publisher to clarify whether a remote embedding API key is required and update registry metadata. 6) Mitigations: run inside a contained environment (dedicated user account or container), inspect/grep for network requests in the Python scripts, and test with non-sensitive example data first. If you need a fully offline option, confirm whether local sentence-transformers models are used instead of remote embeddings and how to force local-only operation.

Type: OpenClaw Skill Name: qui-jasper-recall Version: 1.0.0 The skill bundle implements a functional RAG system but contains critical security vulnerabilities and high-risk patterns. Specifically, 'cli/server.js' and 'extensions/openclaw-plugin/index.ts' use 'execSync' to execute shell commands with user-provided search queries; while there is basic escaping for double quotes, it is insufficient to prevent command injection via other shell metacharacters (e.g., backticks or subshells). Additionally, the system sends potentially sensitive agent memory to an external endpoint (api.heybossai.com) for embeddings. While the inclusion of 'scripts/privacy-check.py' suggests a lack of malicious intent regarding data leakage, the combination of RCE vulnerabilities and external data transmission makes this bundle high-risk for production environments.