merger-model

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses external tools (web_search, web_extract) to gather financial data from public sources such as SEC EDGAR, which is consistent with its stated purpose of transaction modeling. While this creates a surface for indirect prompt injection, it is the primary intended function of the skill and is considered safe under typical use cases.- [COMMAND_EXECUTION]: The instructions reference a local Python script (recalc.py) from the excel-author skill to update the generated Excel workbook. This is a documented cross-skill workflow for spreadsheet automation.- [SAFE]: The skill is adapted from a public repository belonging to Anthropic, a trusted organization, and does not contain any obfuscated code or unauthorized data access patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:44 PM
Security Audit — agent-trust-hub — merger-model