capacitor-platforms

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill encourages the use of a Capawesome MCP server to fetch current documentation via search_docs and get_doc_page tools. Ingesting external web content into the agent's context creates a surface for indirect prompt injection if the source content is compromised.
  • Ingestion points: search_docs and get_doc_page tool outputs from the vendor-hosted MCP server referenced in SKILL.md.
  • Boundary markers: The skill does not specify any delimiters or safety warnings for the agent when processing the fetched documentation.
  • Capability inventory: The skill guides the user through package installation (npm install), Capacitor platform management (npx cap add/sync/run), and modification of package.json scripts (postinstall).
  • Sanitization: No sanitization or validation of the fetched documentation content is mentioned.
  • [COMMAND_EXECUTION]: The skill provides numerous commands for installation, synchronization, and building, such as npm install @capawesome/capacitor-electron, npx cap add, and npx tauri build. These are standard commands for Capacitor and Tauri development environments.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server using the command claude mcp add --transport http capawesome "https://mcp.capawesome.io/mcp". This connects the agent to a remote service managed by the vendor for real-time documentation access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:00 PM
Security Audit — agent-trust-hub — capacitor-platforms