developer-growth-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires reading the user's local chat history (including pastedContents that may contain API keys or passwords) and asks the agent to include "specific evidence from chat history" in the generated report and send it to Slack, which can force verbatim exposure of secrets without any redaction instruction.

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

• Third-party content exposure detected (medium risk: 0.30). In the required workflow, the agent reads and ingests user/tenant-authored chat content from ~/.claude/history.jsonl (including display and pastedContents) from the past 24–48 hours, which is free text that can contain outsider-provided content.