The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill executes a Python script (recalc.py) located within a related skill (excel-author). This is a legitimate inter-skill dependency for recalculating Excel formulas and does not involve executing untrusted remote code.
[EXTERNAL_DOWNLOADS]: The skill references well-known and trusted sources for financial data, such as SEC EDGAR (sec.gov). These are appropriate for the skill's stated purpose of financial modeling and sourcing public company data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including SEC filings, earnings decks, and user-provided templates. While this represents an attack surface for processing untrusted data, the skill's output is limited to generating Excel files, and it does not demonstrate capabilities that would allow for unauthorized command execution or privilege escalation.
[SAFE]: No obfuscation, persistence, privilege escalation, or data exfiltration patterns were detected. All identified behaviors align with the primary purpose of professional financial modeling.

lbo-model