The Agent Skills Directory

[PROMPT_INJECTION]: No evidence of prompt injection attempts. The instructions focus on TypeScript language patterns and do not contain bypass markers, role-play injections, or instructions to ignore safety protocols.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or network operations that could lead to data exfiltration were found.
[OBFUSCATION]: No obfuscated content, such as Base64, zero-width characters, or homoglyphs, was detected in the skill or reference files.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverifiable external dependencies were found. The skill suggests using the typescript-lsp tool for diagnostics, which is a standard development practice.
[PRIVILEGE_ESCALATION]: No commands for privilege escalation, such as sudo or excessive file permission changes, were identified.
[PERSISTENCE]: No persistence mechanisms, such as modifications to shell profiles or scheduled tasks, were found.
[DYNAMIC_CONTEXT_INJECTION]: No use of the dynamic command execution syntax (!command) was detected.
[INDIRECT_PROMPT_INJECTION]: The skill ingests TypeScript code files for analysis. While these are external inputs, the capability is limited to providing type diagnostics via an LSP tool, presenting a negligible security risk surface.

typescript-language