preflight-check

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses the UNIFI_API_KEY environment variable and checks for local .env files to retrieve credentials. It performs an authenticated network request to a local network address (192.168.1.1) to verify connectivity. While credentials are transmitted, the request is directed to the legitimate service endpoint.
  • [COMMAND_EXECUTION]: Executes the 'gh auth status' command via the bash shell to verify the user's GitHub CLI authentication state.
  • [EXTERNAL_DOWNLOADS]: The instructions recommend using the 'python-dotenv' package to manage environment variables from local files.
  • [PROMPT_INJECTION]: The skill processes output from external CLI tools and API endpoints, which constitutes an indirect prompt injection surface.
  • Ingestion points: Output from 'gh' CLI, Atlassian MCP tool responses, and UniFi API JSON data.
  • Boundary markers: No explicit delimiters are used to wrap external content.
  • Capability inventory: Includes shell command execution and network request capabilities.
  • Sanitization: No specific filtering or validation of the external content is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 06:32 PM