fundamental-report-detailed

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied stock tickers and resolved company metadata (such as company name and sector) which are ingested into the agent's context and used to generate reports.
  • Ingestion points: The skill accepts a ticker string from the user and resolves it to CIK and metadata in Step 0, which is then passed to 17 parallel analysis tasks.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external ticker data or fetched metadata as untrusted or to ignore instructions embedded within those strings.
  • Capability inventory: The skill has the ability to dispatch tasks to 17 other skills (including parallel analysis and utility skills) and write files to the local filesystem at reports/YYYY-MM-DD-HH-MM-SS-{TICKER}.md.
  • Sanitization: The skill description does not specify any sanitization, validation, or escaping logic for the user-supplied ticker or the external data fetched during the resolution process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:28 AM
Security Audit — agent-trust-hub — fundamental-report-detailed