dcf-model

Warn

Audited by Socket on Feb 25, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

This SKILL documentation describes a legitimate, specialized DCF model builder with reasonable capabilities for its stated purpose. No direct malicious code is present in the text. The primary security concerns are supply-chain and operational: (1) executing recalc.py/LibreOffice is a download-and-execute pattern that requires trusting the recalc.py source and any dependencies; (2) network calls to MCP servers and web fetches introduce potential exfiltration or credential forwarding risks if API keys or data are mishandled; and (3) the docs do not specify secure handling or provenance for external tools and dependencies. These issues raise a moderate security risk that can be mitigated by: obtaining recalc.py and any helper libraries from trusted, pinned, auditable sources; using least-privilege and transient credentials for MCP/web access; avoiding embedding sensitive secrets/credentials in cell comments; and performing code review on the implementation that performs network calls and process execution. Overall I classify this skill as functionally appropriate but with medium supply-chain risk that requires operational controls.

Confidence: 75%Severity: 75%
Audit Metadata
Analyzed At
Feb 25, 2026, 02:28 AM
Package URL
pkg:socket/skills-sh/anthropics%2Ffinancial-services-plugins%2Fdcf-model%2F@baa2b6e70d3cf61efc6d72070218f2a239219915