pp-yahoo-finance

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and metadata describe the installation of the yahoo-finance-pp-cli tool using npx for the @mvanhorn/printing-press package and go install for the github.com/mvanhorn/printing-press-library repository. These sources are associated with the vendor specified in the author context.
  • [COMMAND_EXECUTION]: The skill is primarily designed to execute shell commands using the yahoo-finance-pp-cli binary to perform financial operations and local database queries via a dedicated sql command.
  • [DATA_EXFILTRATION]: The CLI tool provides a --deliver flag which allows redirecting output to external webhooks. Additionally, the auth login-chrome command involves accessing local browser cookie files (~/yahoo-cookies.json) to facilitate authentication with Yahoo Finance.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests and processes external market data from Yahoo Finance which is then presented to the agent.
  • Ingestion points: External data is retrieved via yahoo-finance-pp-cli and loaded into the agent's context.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers when processing retrieved financial data.
  • Capability inventory: The skill has access to Read Bash and can execute arbitrary CLI flags including data delivery sinks.
  • Sanitization: There is no mention of sanitization or filtering of the incoming financial data before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 11:55 AM
Security Audit — agent-trust-hub — pp-yahoo-finance