Advisory Council
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill has a clear market-analysis purpose, but it asks your agent to run an unreviewed local Python file, so the real behavior cannot be checked from the provided artifacts.
Only install or run this if you know what ~/clawd/advisory_council.py contains and trust it. Inspect the script first, run it in a constrained environment if possible, confirm which API credentials it uses, and do not rely on its trading recommendations without independent verification.
Findings (4)
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.
If run, the script could perform any action allowed by the user's account, including file access, network calls, or environment-variable access.
The skill directly instructs the agent to execute local Python through a shell. Because the Python file is not included in the reviewed artifacts, its behavior is not reviewable.
**You MUST actually execute the Python command using your shell/exec tool.** ... `cd ~/clawd && python3 advisory_council.py`
Do not run this skill unless you have inspected and trust ~/clawd/advisory_council.py. Prefer packaging the script with the skill, pinning dependencies, and requiring explicit user approval before shell execution.
Users cannot verify what code will actually run, and the local script could be missing, stale, tampered with, or different on each machine.
The skill has no installation or provenance details, but SKILL.md depends on running `~/clawd/advisory_council.py`. The executable code, dependencies, versioning, and source are outside the reviewed package.
No install spec — this is an instruction-only skill.
Include the script and dependency lockfile in the skill package, declare required binaries and credentials, and document the source and update mechanism.
Running the script may use a provider account or API key and incur small charges, even though credential handling is not documented in the reviewed artifacts.
The skill discloses use of an external AI provider and a per-run cost, but the registry metadata declares no primary credential or required environment variables.
powered by MiniMax M2.5 ... Cost: ~$0.006 per run
Verify which MiniMax credentials or accounts the script uses, set spending limits, and declare required credential names and scopes.
A user may over-rely on the generated report for financial decisions.
The skill is designed to produce decision-oriented trading recommendations and frames the output as trusted for real decisions.
ACTIONS — 2-3 concrete action items with price levels ... Boss Man trusts the council for real decisions
Treat the report as informational only and require independent review before making trades.