Research Logger Pro

Auto-saves deep search results to SQLite and Langfuse. Combines search with persistent logging — every research query is saved with topic tags, timestamps, a...

Security Scan

The skill mostly does what it says (logs Perplexity search results to SQLite and Langfuse) but includes hard-coded Langfuse keys and a default host that will send your research data to an external tracing instance without clearly documented opt-in — this is unexpected and risky.

Purpose & Capability

Name/description (save search results to SQLite + Langfuse) matches the code: the script runs searches (via an external deep_search module), persists results to a SQLite DB in the agent workspace, and optionally records traces to Langfuse. Requiring PERPLEXITY_API_KEY is consistent with using a Perplexity search integration.

Instruction Scope

SKILL.md instructs only to run the Python script and mentions Langfuse tracing, which is accurate, but the runtime code unconditionally injects default LANGFUSE_SECRET_KEY, LANGFUSE_PUBLIC_KEY, and LANGFUSE_HOST values (os.environ.setdefault). That behavior means research queries, metadata and results could be sent to the hard-coded Langfuse endpoint even if the user did not configure Langfuse — the SKILL.md does not disclose the specific keys/host or that a developer-controlled tracing instance will be used by default.

Install Mechanism

There is no install spec (instruction-only skill with one script). Nothing is downloaded or extracted during install, which limits risk. The script does attempt to import optional 'langfuse' and an external 'deep_search' module; neither is bundled, so runtime dependencies must be available.

Credentials

Declared required env var is only PERPLEXITY_API_KEY which is proportional. However the script contains hard-coded Langfuse secret/public keys and a default LANGFUSE_HOST embedded in code — these are effectively hidden credentials and will cause telemetry to flow to that host by default. The SKILL.md does not declare LANGFUSE_* vars as required or optional, so the user may not expect data to be sent to an external tracing instance tied to those embedded keys.

Persistence & Privilege

The skill writes to a SQLite DB under ~/.openclaw/workspace/.data/sqlite/agxntsix.db (within the agent workspace) and does not request broader system privileges or always: true. It doesn't modify other skills or system-wide configs.

Scan Findings in Context

[hardcoded-langfuse-keys] unexpected: The script sets LANGFUSE_SECRET_KEY, LANGFUSE_PUBLIC_KEY, and LANGFUSE_HOST via os.environ.setdefault to hard-coded values (including a secret-like key). This embeds credentials/telemetry configuration in the shipped code and will route traces to the specified host by default.

[external-dependency-deep_search] expected: The script imports from deep_search (from deep_search import search) but the deep_search module is not bundled with the skill. This is expected if deep_search is an external tool the skill wraps; the user should verify where that module comes from and what it sends/records.

What to consider before installing

This skill largely does what it claims (logs Perplexity search results to a local SQLite DB and to Langfuse tracing), but it ships with hard-coded Langfuse keys and a default Langfuse host that will cause your research queries and results to be sent to that tracing instance by default. Before installing or using: 1) Do not run the skill with sensitive queries until you are comfortable with where traces go. 2) Inspect or remove the hard-coded LANGFUSE_* values in scripts/research_logger.py (or override them in your environment) so telemetry does not go to an unknown instance. 3) Confirm the provenance and behavior of the deep_search module the script imports (it is not bundled here). 4) If you want Langfuse tracing, prefer configuring your own LANGFUSE_HOST and keys rather than using embedded keys; ask the author to remove embedded secrets or make telemetry opt-in. If you cannot validate the destination and keys, treat the skill as risky for confidential research.

Research Logger 📝🔬

Search + auto-save pipeline. Every research query is logged to SQLite with Langfuse tracing.

When to Use

• Research that you want to save and recall later
• Building a knowledge base from repeated searches
• Reviewing past research on a topic
• Creating an audit trail of research decisions

Usage

# Search and auto-log
python3 {baseDir}/scripts/research_logger.py log quick "what is RAG"
python3 {baseDir}/scripts/research_logger.py log pro "compare vector databases" --topic "databases"

# Search past research
python3 {baseDir}/scripts/research_logger.py search "vector databases"

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

Credits

Built by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.

📅 Need help setting up OpenClaw for your business? Book a free consultation