The Agent Skills Directory

[NO_CODE]: The skill is composed exclusively of natural language instructions in markdown format and does not contain any executable scripts, binaries, or configuration files.\n- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were identified during the analysis of the skill content.\n- [PROMPT_INJECTION]: The instructions are strictly limited to structural editing tasks and do not include patterns designed to bypass AI safety filters, ignore prior instructions, or extract system prompts.\n- [DATA_EXFILTRATION]: The skill does not contain any network-related commands (e.g., curl, wget) or logic that would facilitate the transmission of data to external servers.\n- [SAFE]: While the skill processes external text data (SKILL.md), it does not define any capabilities (such as tool use or file writing) that could be exploited via indirect prompt injection.

copywriting