pp-yahoo-finance

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes examples that pass session secrets on the command line (e.g., --cookies ~/yahoo-cookies.json and a --crumb value like "abc123"), which encourages embedding session tokens/crumbs as literal arguments that an LLM could be asked to reproduce verbatim, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to run yahoo-finance-pp-cli commands that fetch live data from Yahoo Finance (e.g., quote, chart, screener, trending, the session bootstrap/auth login-chrome flow and data-source auto|live|local), so the agent ingests public Yahoo content which can directly influence subsequent tool use and decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and running remote code at runtime (e.g., via "npx -y @mvanhorn/printing-press install yahoo-finance --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/commerce/yahoo-finance/cmd/yahoo-finance-pp-cli@latest"), which fetches and executes external code and is a required dependency for the skill to operate.