The Agent Skills Directory

[SAFE]: The skill document defines a logical framework (methodology) for prioritizing actions during a security engagement based on evidence. It does not include any executable code or instructions that interact with the host system.
[NO_CODE]: The skill does not list any tools in its configuration and contains no shell scripts, Python code, or Node.js scripts, removing the possibility of common attack vectors like command injection or remote code execution.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process results from previous tasks (which could theoretically contain malicious data), the skill lacks any capabilities (tools, file writes, or network access) that could be exploited via such an injection.

tradecraft-pivot-decisions