skills/zapabob/skills/comps-analysis/Gen Agent Trust Hub

comps-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions to execute a specific local Python script recalc.py (associated with a peer skill named excel-author) to recalculate the generated spreadsheet.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest financial and trading information from external sources including web searches, SEC EDGAR filings, and third-party financial data providers (MCPs). While the instructions focus on numerical data extraction, processing untrusted data from the web or external APIs represents an indirect prompt injection surface if the sourced content contains adversarial text designed to influence the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 12:07 PM