The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown-based instructions for an AI agent and does not include any scripts, binaries, or executable code blocks.
[SAFE]: The operations described involve creating local directory structures and templating README files based on user-provided metadata, which are standard project management tasks.
[PROMPT_INJECTION]: No evidence of malicious instructions, jailbreak attempts, or safety filter bypasses was found in the content.
[DATA_EXFILTRATION]: The skill does not request any network operations or access to sensitive system paths like credentials or SSH keys.
[COMMAND_EXECUTION]: No shell commands, subprocess spawning, or system-level executions are present in the skill definition.
[SAFE]: Regarding indirect prompt injection, the skill ingests user input (initiative details) in SKILL.md and lacks explicit boundary markers or sanitization; however, its capabilities are strictly limited to file system organization within the local workspace, posing no significant security risk.

setup-initiative