TradingView Screener
PassAudited by ClawScan on May 10, 2026.
Overview
This skill appears to match its stated purpose of screening TradingView market data, with review-worthy but purpose-aligned dependency installation and custom expression evaluation.
Before installing, review the dependency list and install script, and only run signal YAML files you trust. The reviewed artifacts do not show credential use, trading execution, destructive actions, or hidden data exfiltration.
Findings (2)
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.