cline-session-history

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to print full prompts and full conversation transcripts and to export session files, which will cause any secrets contained in those session contents (API keys, tokens, passwords) to be output verbatim — creating a direct exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.70). This skill reads outsider-authored free text from the local Cline session transcript files (~/.cline/data/sessions/**/<id>.messages.json), which can contain arbitrary user/third-party conversation content, and then prints it (including text blocks) to stdout rather than safely constraining it before any LLM context ingestion.