pp-digg

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses live, public third-party content (e.g., Digg HTML via "feed raw", Digg APIs such as /api/search/stories used by the search command, the posts <clusterUrlId> output which returns X/Twitter user-generated post bodies, and the events pipeline stream) and instructs agents to consume those results with --agent to drive alerts, evidence, sentiment, and follow-up actions, so untrusted user-generated content can materially influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs installing a required CLI via the runtime command "npx -y @mvanhorn/printing-press install digg --cli-only", which fetches and executes remote code from the npm registry to produce the digg-pp-cli dependency.