both-stock-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill orchestrates a multi-step pipeline by instructing the agent to execute local Python scripts (e.g., skills/har-to-api/scripts/fetch.py, skills/pipeline/business-drivers/scripts/sensitivity.py, skills/stock-grill/scripts/read_report.py). These commands are task-aligned and restricted to internal skill directories.
  • [DYNAMIC_EXECUTION]: The skill generates a filing-grade HTML research document using a bash heredoc. This is a standard reporting mechanism and does not involve the execution of untrusted code.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data (ticker facts and market data) via the har-to-api utility. While this represents a data ingestion surface, the risk is mitigated by the structured nature of financial metrics and the use of dedicated internal scripts to process the data.
  • [SAFE]: The workflow follows financial analysis best practices (the Damodaran framework), confirms market parameters to ensure calculation accuracy, and includes explicit disclaimers regarding financial advice.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 01:31 PM
Security Audit — agent-trust-hub — both-stock-analysis