confluence

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that embed credentials (password/API_TOKEN and plaintext username/password in a curl request) directly in code/commands, which encourages the agent to require or output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s Confluence skill exposes runtime reads of Confluence page bodies and space searches (e.g., get_page_by_id with expand='body.storage' and cql/search), so if an outsider can author Confluence content that the workflow queries/loads, that free text becomes LLM-ingested.