report-card Audit report.

Warnings

• Permission surface may require sandboxing
• Financial research output is not financial advice; require human review before any live investment decision
• Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
• The skill is tightly coupled to the bullshit-detector repository (tally.py, report format). It may not be reusable outside that ecosystem, but that is acceptable given its specific purpose.
• The script uses subprocess to invoke tally.py; if tally.py is not found, it warns and renders. This is a reasonable fallback but could be a security concern if a malicious tally.py is placed in the path. However, the script only calls it with the report path, and the user controls the environment.
• Financial research output is not financial advice; require human review before any live investment decision.
• This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
• Quality score needs review
• Permission surface needs review: shell or command execution, filesystem or document access
• Stars/forks activity: 140 stars, 10 forks; issue activity unavailable in current metadata
• Permission surface: shell or command execution, filesystem or document access

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.