Research Logger

AI research pipeline with automatic SQLite logging and Langfuse tracing

Security Scan

The skill mostly does what it says (logging research to SQLite and optional Langfuse tracing) but contains hard-coded Langfuse secret/public keys and defaults that are disproportionate and unexpected, and the runtime relies on an external deep_search module that is not included — these inconsistencies merit caution.

Purpose & Capability

The name/description claim an AI research logger using Perplexity and Langfuse. The code implements SQLite logging and optional Langfuse tracing (coherent), but the registry metadata lists no required env vars while SKILL.md documents PERPLEXITY_API_KEY and Langfuse vars — a mismatch. The script imports a deep_search module that is not included, so it depends on external code that could alter behavior.

Instruction Scope

The SKILL.md instructions are narrowly scoped to searching and saving results, which aligns with the script. However the script will create and write a DB at ~/.openclaw/workspace/.data/sqlite/agxntsix.db and will use Langfuse client (if installed) to send traces to a host. The code also silently injects default LANGFUSE_* credentials into the environment if none exist, causing network telemetry to be sent without an explicit instruction in SKILL.md to use those defaults.

Install Mechanism

No install spec is provided (instruction-only with a bundled script). That lowers risk from arbitrary installers. It does require Python packages (requests, langfuse) but does not auto-install them.

Credentials

SKILL.md lists PERPLEXITY_API_KEY and Langfuse keys as expected. But the script embeds hard-coded LANGFUSE_SECRET_KEY and LANGFUSE_PUBLIC_KEY values and a LANGFUSE_HOST default via os.environ.setdefault — embedding secrets in code is disproportionate and risky. The registry declared no required env vars, which is inconsistent. The script will use these embedded keys if the user doesn't supply their own.

Persistence & Privilege

The skill does not request always: true or modify other skills. It writes a local SQLite DB under the user's home (~/.openclaw/...), which is consistent with a logging tool but does create persistent data on disk.

What to consider before installing

This skill largely does what it says (logs research to a local SQLite DB and can send traces to Langfuse), but there are red flags you should address before running it: 1) The script contains hard-coded Langfuse keys and a default LANGFUSE_HOST — remove these defaults and provide your own keys if you want tracing; embedded secrets can route your data to an external endpoint. 2) SKILL.md and registry metadata disagree about required env vars; confirm you must set PERPLEXITY_API_KEY and Langfuse vars. 3) The script imports deep_search, which is not included — inspect or provide a trusted deep_search implementation before use (it likely performs the web searches and may require your Perplexity key). 4) The script will create and write a DB at ~/.openclaw/workspace/.data/sqlite/agxntsix.db — if that location is sensitive, change it. 5) If you want to run this, do so in a sandbox or review network egress (where traces/searches are sent). If you cannot verify or remove the hard-coded keys and validate deep_search, do not run this in production or on sensitive machines.

AI research pipeline with automatic logging. Search via Perplexity, auto-save results to SQLite with topic/project metadata, full Langfuse tracing. Never lose a research session again.

Usage

# Search and auto-save to SQLite
python3 scripts/research_logger.py log quick "what is RAG?"

# Research with topic tagging
python3 scripts/research_logger.py log pro "compare vector databases" --topic "AI infrastructure"

# Search past research entries
python3 scripts/research_logger.py search "AI"

# View recent entries
python3 scripts/research_logger.py recent --limit 5

Requirements

• PERPLEXITY_API_KEY environment variable
• LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, LANGFUSE_HOST (optional, for tracing)
• Python 3.10+
• requests, langfuse packages
• SQLite (included with Python)

Credits

Built by AgxntSix — AI ops agent by M. Abidi 🌐 agxntsix.ai | Part of the AgxntSix Skill Suite for OpenClaw agents