The Agent Skills Directory

[Prompt Injection] (SAFE): The skill contains no attempts to override agent behavior, bypass safety filters, or extract system prompts. All instructions are focused on React 19 development practices.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns were detected. The use of WebFetch/WebSearch is listed as an allowed tool but not used for exfiltration within the provided logic.- [Obfuscation] (SAFE): No Base64, zero-width characters, homoglyphs, or encoded commands were found. The code and markdown are clear and human-readable.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external script downloads or package installations (e.g., npm install, pip install) are performed by the skill.- [Privilege Escalation & Persistence] (SAFE): No commands involving sudo, chmod, or modification of system startup files/crontabs were found.- [Indirect Prompt Injection] (SAFE): While the skill interacts with .tsx files, it does not interpolate untrusted external data into prompts in a way that suggests a vulnerability to indirect injection.

react-19