pp-edgar

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public SEC EDGAR content (e.g., via commands like "filings browse", "filings get", "efts", "primary-sources", and "sections" that return raw EDGAR HTML/Atom and filing bodies from sec.gov), so the agent reads third-party web-hosted filing text that could contain instructions or influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite installs remote code at runtime via the npx command "npx -y @mvanhorn/printing-press install edgar --cli-only", which fetches and executes installer code the skill requires to provide its CLI, so it is a runtime external dependency that can execute remote code.