pp-framer

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the framer-pp-cli and framer-pp-mcp tools from the vendor's GitHub repository using go install and npx.
  • [COMMAND_EXECUTION]: The skill invokes the framer-pp-cli binary to perform project operations, which internally uses a Node.js bridge (bridge/framer-bridge.mjs) to communicate with the Framer Server API.
  • [INDIRECT_PROMPT_INJECTION]: The skill has attack surfaces where untrusted external data is ingested and processed.
  • Ingestion points: The cms-sync command reads from local CSV/JSON files, and migrate-scrape retrieves content from external URLs.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded content are provided.
  • Capability inventory: The tool has broad project modification capabilities, including updating CMS items, changing canvas nodes, and performing network operations via the API bridge.
  • Sanitization: No sanitization or validation of the ingested external content is described.
  • [DATA_EXFILTRATION]: The skill provides an output delivery mechanism via the --deliver webhook:<url> flag, which allows routing project data and command results to arbitrary external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:46 AM
Security Audit — agent-trust-hub — pp-framer