The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external C/C++ source code files which represent untrusted data that could potentially contain malicious instructions.
Ingestion points: Source code files with extensions such as .c, .h, .cpp, .cc, .cxx, .hpp, .hxx.
Boundary markers: The instructions do not define specific delimiters to separate untrusted file content from agent instructions.
Capability inventory: The skill interacts with the file system and uses run_command to execute clangd for analysis.
Sanitization: There is no explicit sanitization of the source code or the diagnostics output generated by the language server.
[COMMAND_EXECUTION]: The skill instructs the agent to use run_command to execute the clangd binary for language diagnostics and symbol inspection, which is the intended functional purpose of the integration.

clangd-lsp