ai-presentation-maker

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to create documents, posing a potential risk of indirect prompt injection.
  • Ingestion points: The create_document and update_document tools in SKILL.md accept provided_content, source_urls, and files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill body.
  • Capability inventory: The skill can read (get_document), modify (update_document), and export documents (export_document) as defined in SKILL.md.
  • Sanitization: The instructions do not define any sanitization or validation logic for the input content.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's API at https://app.slaide.de/api/mcp via an MCP server connection. This network activity is a functional requirement for interacting with the Slaide service.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 04:34 PM