management-deep-dive

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes untrusted information from the web to perform its analysis.
  • Ingestion points: Untrusted data enters the agent's context through web_search, get_stock_news, and public employee/customer feedback sources (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or clear separation between the agent's instructions and the untrusted data fetched from the web.
  • Capability inventory: The skill has the ability to write files to the local filesystem using write_file and can coordinate complex tasks through run_swarm (SKILL.md).
  • Sanitization: No explicit validation or filtering of the retrieved web content is documented in the instructions.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from several external sources, including trusted financial repositories like SEC filings and well-known news services, as part of its management assessment process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 10:24 PM
Security Audit — agent-trust-hub — management-deep-dive