stock-announcements

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the requests library to download announcement PDFs from Eastmoney's official domain (pdf.dfcfw.com). This is a well-known financial service provider and is considered a safe data source for this context.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external stock announcements and PDF files. Evidence: 1. Ingestion points: External data enters via ak.stock_notice_report and requests.get(pdf_url) in announcements.py. 2. Boundary markers: The skill does not use delimiters or instructions to ignore embedded commands in the fetched data. 3. Capability inventory: The agent is instructed to interpret, categorize, and summarize the content. 4. Sanitization: No significant sanitization or escaping of the remote content is performed before presentation to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 02:04 AM