stockbee-20pct-study

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches market universe data and historical stock prices from Financial Modeling Prep (FMP). This interaction is handled by the FMPClient in scripts/run_20pct_study.py using the requests library. The data retrieval targets a well-known financial provider and is limited to public market data required for the study's primary function.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and summarizes external catalyst and news data, creating an entry point for untrusted content. However, the data is processed procedurally and does not influence the agent's logic flow.\n
  • Ingestion points: News data provided via the --news-json CLI argument or retrieved through the FMP API.\n
  • Boundary markers: None identified in the report templates.\n
  • Capability inventory: The skill performs local file system writes to update state and generate reports.\n
  • Sanitization: The enrich_events_with_news function in scripts/run_20pct_study.py normalizes whitespace and truncates news summaries to 500 characters.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 05:42 PM
Security Audit — agent-trust-hub — stockbee-20pct-study