confluence-automation

Warn

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure a third-party MCP server using the URL https://rube.app/mcp (SKILL.md). This external endpoint is not from a verified or trusted organization.
  • [REMOTE_CODE_EXECUTION]: By adding the MCP server, the agent dynamically discovers and executes tool definitions provided by the remote endpoint. This creates a dependency on remote logic that is not distributed with the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources that may contain malicious instructions.
  • Ingestion points: Untrusted data enters the agent context via tool outputs from search and retrieval tools, such as CONFLUENCE_SEARCH_CONTENT and CONFLUENCE_GET_PAGE_BY_ID (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore embedded instructions when processing results.
  • Capability inventory: The skill includes capabilities to modify the environment, such as page creation, updates, and deletion (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from Confluence before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 6, 2026, 06:07 AM
Security Audit — agent-trust-hub — confluence-automation