makers-deploy

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the vendor-provided edgeone CLI tool through the official NPM registry via npm install -g edgeone@latest.
  • [COMMAND_EXECUTION]: The skill uses the edgeone CLI to execute multiple operations including authentication checks, login procedures, and project deployments.
  • [CREDENTIALS_UNSAFE]: The skill handles sensitive API tokens. It follows secure management practices by saving these tokens to a local .edgeone/.token file and ensuring this file is excluded from version control by updating the project's .gitignore.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it parses text output from the edgeone CLI to extract project identifiers and deployment URLs.
  • Ingestion points: Output from the edgeone pages deploy command as described in SKILL.md.
  • Boundary markers: None identified in the prompt templates to separate tool output from instructions.
  • Capability inventory: Subprocess execution and file system write access in SKILL.md.
  • Sanitization: No validation or sanitization of the CLI output is implemented before the agent processes the extracted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 03:21 AM
Security Audit — agent-trust-hub — makers-deploy