The Agent Skills Directory

[SAFE]: The skill provides instructions for system and library call tracing using standard Linux utilities (strace, ltrace).
[COMMAND_EXECUTION]: Provides numerous bash command examples for debugging; all commands are relevant to the skill's primary purpose and do not contain malicious payloads.
[INDIRECT_PROMPT_INJECTION]: The skill guides the agent in processing tool output (e.g., via grep or awk). While processing external data is a potential attack surface, the instructions are safe and standard for the intended use case.

strace-ltrace