confluence-expert

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the extraction and analysis of external documentation from Confluence, which represents a standard surface for indirect prompt injection. This is expected behavior given the skill's purpose as a Confluence management assistant.
  • Ingestion points: The skill uses a Confluence MCP Server to Extract documentation for analysis and Search content (SKILL.md).
  • Boundary markers: There are no specific instructions provided to the agent regarding delimiters or the presence of untrusted instructions within the processed Confluence pages.
  • Capability inventory: The skill possesses the capability to Create and manage spaces, Create, update, and delete pages, and Configure permissions via the MCP server (SKILL.md).
  • Sanitization: No explicit sanitization or content validation procedures are defined for the documentation retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 07:02 PM
Security Audit — agent-trust-hub — confluence-expert