The Agent Skills Directory

[SAFE]: No malicious patterns or security risks identified. The skill operates entirely within the local workspace to perform its stated function of strategy validation.- [PROMPT_INJECTION]: The skill incorporates content from local research files (such as strategy-brief.md) into sub-agent prompts. While this creates a surface for indirect prompt injection, the risk is localized to the user's project files, and the behavior is necessary for the skill's core purpose.- [COMMAND_EXECUTION]: The skill uses a structured Task orchestration tool to invoke specialized sub-agents. These are internal LLM calls rather than operating system command executions. File operations are limited to reading and appending to markdown files in the research directories.

expert-validator