The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from project configuration files which could potentially contain malicious instructions that influence the agent's behavior.
Ingestion points: package.json, tsconfig.json, vite.config.ts, next.config.js, remix.config.js, capacitor.config.ts, and capacitor.config.json (as described in Step 1 of SKILL.md).
Boundary markers: Absent; the instructions do not define delimiters or specific warnings to ignore content within the analyzed files.
Capability inventory: The skill instructs the agent to execute shell commands (npm run build, npx cap sync, npx cap run) in SKILL.md and generate or modify source files in the project directories.
Sanitization: Absent; no explicit validation or escaping of the configuration data is mentioned.
[COMMAND_EXECUTION]: The skill guides the user to run standard Capacitor CLI commands for project synchronization and deployment.
Evidence: Procedures in SKILL.md suggest using npx cap sync and npx cap run with various platform-specific flags.

capacitor-react