continue-claude-code-work

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires accepting a user-provided Claude Code Session ID and instructs the agent to invoke a tool with "the exact Session", which forces embedding the session identifier verbatim into tool/request arguments and thus risks secret exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). The continue-claude-code-work skill’s runtime workflow explicitly reads “Claude Code history” for a user-provided [session-id] via daymade-claude-code:read-claude-code-history, which will ingest outsider-authored free text from that session.