capacitor-plugin-upgrade-v5-to-v6

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEDYNAMIC_CONTEXT_INJECTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the dynamic context injection syntax (!) to execute shell commands when the skill is loaded. It runs a Node.js script to extract Capacitor-related peer dependencies from package.json and uses a find command to locate standard native directories (ios, android, example-app). These commands are used solely for environmental discovery and do not involve credential harvesting or network exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from package.json to establish a project snapshot.
  • Ingestion points: Reads package.json via a Node.js script in SKILL.md.
  • Boundary markers: The output is formatted as key-value pairs (package.name=...).
  • Capability inventory: The skill has access to Bash(node -e *), Bash(find *), and suggests running npm install and native build tools.
  • Sanitization: The extraction script is narrowly scoped to only output keys that start with @capacitor/, preventing unrelated data from entering the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 07:08 AM