figma-debug-bundle

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes a local shell script (figma-debug-bundle.sh) to collect environment metadata and API response metrics. It utilizes chmod +x to grant execution permissions to the generated script, which is a standard pattern for CLI-based diagnostic tools.\n- [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect injection by ingesting untrusted data from the Figma REST API into the agent's context during the diagnostic process.\n
  • Ingestion points: API response bodies captured in me.json and file-meta.json within the shell script.\n
  • Boundary markers: Not present; the raw or filtered data is processed directly by shell utilities.\n
  • Capability inventory: The skill has permissions for network operations (curl), file system manipulation (tar, mkdir, rm), and command execution (bash, node, jq).\n
  • Sanitization: The skill implements specific sanitization logic using jq to redact sensitive fields such as email and img_url from the user profile data before final archiving.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:45 AM
Security Audit — agent-trust-hub — figma-debug-bundle