TradingView Screener
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: tradingview-screener Version: 1.1.0 The OpenClaw AgentSkills bundle is classified as benign. The `install.sh` script performs standard virtual environment setup and dependency installation from a local `requirements.txt` without suspicious external calls. The Python scripts (`screen.py`, `signal_engine.py`, `signal_types.py`) primarily interact with the `tvscreener` library and `pandas` for data processing. Crucially, the `signal_types.py` module includes robust `validate_expression` logic with a strict character whitelist and a keyword blacklist (e.g., `import`, `exec`, `eval`, `open`, `os`, `sys`, `lambda`) to prevent arbitrary code execution when using `df.eval()`. The `SKILL.md` and other documentation files clearly describe the skill's functionality and do not contain any prompt injection attempts or instructions for malicious actions.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A custom signal file can influence the screening logic that the skill evaluates.
Custom signal expressions from YAML are dynamically evaluated with pandas after validation. This is an expected feature for computed trading signals, but untrusted or malformed YAML can affect what calculations are run.
validate_expression(expr)
# Resolve field names in expression to actual DataFrame column names
resolved_expr = _resolve_expr_columns(df, expr)
try:
mask = df.eval(resolved_expr)Use signal YAML files you trust, review any expr fields before running them, and keep the expression whitelist restrictions in place.
Installing the skill may download newer dependency code from the Python package ecosystem.
The documented install flow installs dependencies using range constraints rather than pinned or locked versions, so future installs may fetch package versions not reflected in the reviewed artifacts.
tvscreener>=0.2.0 pandas>=2.0.0 pyyaml>=6.0 pytest>=7.0.0
Review install.sh and requirements.txt before setup; consider pinning exact package versions if reproducibility is important.