capgo-cloud-migration

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill directs the agent to scan for sensitive information within the project, including searching for CAPGO_API_KEY in CI/CD pipeline configurations and private key files such as .capgo_key_v2 in the project root.
  • [EXTERNAL_DOWNLOADS]: The skill installs the @capawesome/capacitor-live-update package from npm and utilizes the @capawesome/cli tool. These resources originate from the skill's author, capawesome-team.
  • [COMMAND_EXECUTION]: The agent is instructed to run multiple shell commands using npm and npx for package management, cloud authentication, and application configuration.
  • [PROMPT_INJECTION]: The skill identifies and processes information from various project files, which serves as an attack surface for indirect prompt injection.
  • Ingestion points: Project files including package.json, capacitor.config.ts, and CI/CD workflow files (.github/workflows/*.yml, .gitlab-ci.yml, bitrise.yml, Jenkinsfile, azure-pipelines.yml).
  • Boundary markers: The instructions do not employ specific boundary markers or 'ignore' instructions when processing the content of these external files.
  • Capability inventory: The skill possesses capabilities to install software, modify project files, and perform network requests through vendor-provided CLI tools.
  • Sanitization: The skill lacks explicit sanitization or validation mechanisms for the data ingested from project configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 08:35 PM
Security Audit — agent-trust-hub — capgo-cloud-migration