Skills
skills/0juano/agent-skills/edgeone-pages-deploy/Gen Agent Trust Hub

edgeone-pages-deploy

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION] (LOW): The skill transmits local HTML file content to an external endpoint (https://mcp-on-edge.edgeone.app/mcp-server).
  • Evidence: scripts/deploy.sh uses curl to POST the contents of $HTML_FILE to an external URL.
  • Context: This behavior is the primary intended function of the skill (deployment), which normally reduces severity. However, because the destination domain is not on the trusted whitelist and involves no authentication, it is flagged as LOW severity.
  • [COMMAND_EXECUTION] (SAFE): The skill executes local system commands for processing data.
  • Evidence: scripts/deploy.sh calls bash and python3 -c to encode/decode JSON and execute network requests.
  • Context: These commands operate on local data and parameters provided during execution and do not involve downloading or executing remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM