The Agent Skills Directory

[SAFE]: The skill instructions define a standard organizational workflow for ticket creation and status updates. No patterns of data exfiltration, privilege escalation, or persistence were detected.- [INDIRECT_PROMPT_INJECTION]: The skill ingests operator input through the /idea command and places it verbatim into ticket bodies. While this creates an ingestion point for untrusted data, it is the primary intended function of the skill and does not include instructions to bypass safety protocols.- [NO_CODE]: The skill consists of markdown instructions and evaluation criteria without including or executing external scripts, binaries, or unverifiable dependencies.

idea