jeecg-onlreport

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to ask the user for an API token (X-Access-Token) and pass it directly into Python scripts or CLI commands as arguments, which can lead to secret exposure in logs and the LLM's context.

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

• Third-party content exposure detected (medium risk: 0.30). The skill requires the agent to query and read existing JeecgBoot Online reports and SQL queries via API (list_all_reports_table, list_reports, query_report), which may contain third-party or outsider-authored report names, codes, and SQL statements.