confluence-distill

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md workflow (Steps 2–4) explicitly requires the agent to search a user-specified Confluence instance via REST or Membrane and GET page bodies (body.storage/body.view) which the agent must read and distill into a new Agent Skill package, meaning arbitrary user-generated wiki pages can directly influence the agent's decisions and generated actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). Flagged because the skill explicitly fetches Confluence page bodies at runtime from the user's Confluence REST API base (e.g., https://<site>.atlassian.net/wiki -> /rest/api/...), and that fetched content is injected into the agent’s context and used to generate/drive the new skill (i.e., remote content directly controls prompts/instructions).