The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown and reference files focused on information distillation. No malicious patterns, obfuscation, or unauthorized data access were identified.
[NO_CODE]: The skill is entirely composed of text-based instructions and does not bundle any executable scripts, binaries, or automated installation steps, which minimizes the attack surface.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-supplied sources (Workflow Step 1 in SKILL.md). No specific boundary markers or sanitization procedures are defined. However, the capability inventory is limited to text generation and elective research tool usage, lacking high-risk operations like file writing or arbitrary command execution, making the surface safe for its intended purpose.

synthesize