session-handoff

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to read the environment variable CLAUDE_CODE_SESSION_ID and embed the full UUID verbatim into files, engram entries, and the printed resume command, requiring the LLM to handle and output a sensitive session token.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill deliberately records full conversation summaries and the full CLAUDE_CODE_SESSION_ID to disk (git-tracked docs/handoffs/) and to an external memory service (mem_save / mem_session_summary) without user interaction or consent, which constitutes intentional data exfiltration and exposes session identifiers that could enable session hijack or resume.