The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown providing guidance on evidence gathering, auditing methodology, and reporting standards. No malicious patterns were detected.
[NO_CODE]: The files contain only documentation and instructions. There are no scripts, executables, or code blocks intended for execution by the agent or the system.
[EXTERNAL_DOWNLOADS]: The skill does not perform any network operations or fetch external resources. All content is contained within the provided markdown files.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use the dynamic context injection syntax (!command) to execute shell commands at load time.
[INDIRECT_PROMPT_INJECTION]: The skill provides defensive guidance for handling evidence (such as printing raw state beside decisions and naming search spaces), which helps mitigate potential confusion from untrusted data by encouraging explicit verification.

evidence-rules