The Agent Skills Directory

[SAFE]: No direct malicious patterns, obfuscation, or data exfiltration attempts were found. The skill follows standard operational guidelines for a development assistant.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted project data.
Ingestion points: The skill analyzes tsconfig.json, package.json, build configurations, and source code files from the project environment.
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when reading project files.
Capability inventory: The agent is instructed to use tools including tsc, eslint, prettier, jest, webpack, vite, and tsx.
Sanitization: No sanitization or validation logic is defined for the content processed from project files.
[REMOTE_CODE_EXECUTION]: No unauthorized remote code execution or untrusted downloads were detected. The listed MCP tools are standard development utilities.
[DATA_EXFILTRATION]: No access to sensitive system paths or external network requests targeting non-whitelisted domains were identified.

typescript-pro