The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No instructions found that attempt to override agent behavior, extract system prompts, or bypass safety filters. The skill adheres to its stated instructional purpose.- [DATA_EXFILTRATION] (SAFE): No hardcoded secrets, credentials, or sensitive file paths were detected. References to localStorage and cookies are limited to code examples demonstrating caching for performance.- [REMOTE_CODE_EXECUTION] (SAFE): The skill consists entirely of Markdown files and templates. There are no shell scripts, Python files, or JavaScript files that execute during use. No remote download/execution patterns identified.- [OBFUSCATION] (SAFE): All text is human-readable. No Base64, zero-width characters, or other encoding techniques were used to hide malicious logic.- [COMMAND_EXECUTION] (SAFE): No use of dangerous system-level functions or subprocess spawning found in the documentation examples.- [SAFE_PRACTICES] (INFO): The skill actively encourages security best practices in references/bounded-iteration.md by teaching how to prevent Denial of Service (DoS) through bounded loops and recursion limits.

accelint-ts-performance