The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and execute steps from an external plan file. While this introduces a surface for indirect instructions, the skill mitigates risk by requiring the agent to critically review the plan for concerns before starting and providing clear 'stop and ask' criteria for blockers or unclear instructions.
[SAFE]: No malicious patterns such as obfuscation, credential exfiltration, unauthorized network access, or persistence mechanisms were detected. The skill focuses on workflow management and integration with other development tools within the project scope.

executing-plans