graphify

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask for and then directly embed Neo4j credentials (URI, user, password) into a push command, which requires the LLM to handle and output secret values verbatim — an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). In Step 3B2, the required runtime workflow dispatches the subagent to read arbitrary files under the user-provided input path (and also ingests outsider-provided URLs via /graphify add <url> into ./raw), so outsider-authored free text can be ingested by the LLM without selecting a specific trusted item first.