deploy-surge

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute several shell commands including rtk, bun, and openssl. These are used for environment checks, package installation, random slug generation, and interacting with the Surge CLI.
  • [EXTERNAL_DOWNLOADS]: The skill performs an external download by prompting the installation of the surge package via bun install -g surge if the command is not present on the system. Surge is a well-known service for static site hosting.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the list subcommand which processes untrusted data stored in a local inventory file.
  • Ingestion points: The surge-inventory.yaml file is read in SKILL.md to display a summary table of previous deployments.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used when displaying the inventory data.
  • Capability inventory: The skill has access to shell execution (Bash) and file system operations (Read, Edit, Write).
  • Sanitization: There is no evidence of sanitization for the description or slug fields which are provided by the user during the deployment process and later stored in the YAML inventory.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:31 PM
Security Audit — agent-trust-hub — deploy-surge