capgo-cloud-migration

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via npm and npx to manage project dependencies and interact with vendor-specific CLI tools (@capgo/cli and @capawesome/cli). These operations are necessary for the stated migration purpose.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of packages from the public npm registry. All referenced packages (@capawesome/capacitor-live-update, @capawesome/cli) are official resources belonging to the vendor, 'capawesome-team'.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it instructs the agent to read and analyze untrusted local project data to determine migration steps.
  • Ingestion points: The agent reads package.json, capacitor.config.ts, and various CI/CD configuration files (GitHub Actions, GitLab CI, etc.) from the user's project.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore potential commands embedded in the project files.
  • Capability inventory: The agent has the capability to execute shell commands (npm, npx), modify the filesystem, and perform network logins via the CLI.
  • Sanitization: The skill does not explicitly describe sanitization or validation of the data (like App IDs or channel names) extracted from project files before passing them to CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 11:18 AM
Security Audit — agent-trust-hub — capgo-cloud-migration