The Agent Skills Directory

[SAFE]: The skill instructions define a process for bounded research and task assessment. The commands and tools mentioned, such as /route, /retrieve-memory, and doctrine search, appear to be internal agent tools for context management and project navigation.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data via the $ARGUMENTS placeholder and external documents. While this creates a surface for indirect prompt injection, the skill lacks high-risk capabilities like network exfiltration of sensitive files or arbitrary shell execution that would make this surface exploitable for malicious purposes. The primary output is a research assessment presented to the user.

preflight