The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and YAML configuration. No executable scripts, binaries, or active shell commands are present in the skill files.
[NO_CODE]: The skill provides instructions and references for modifying a target codebase but does not ship with any internal code to be executed by the agent environment.
[PROMPT_INJECTION]: No patterns of instruction override, safety filter bypass, or role-play injection were detected. The language is professional and focused on system architecture.
[DATA_EXFILTRATION]: There is no evidence of sensitive file access, credential harvesting, or unauthorized network operations. References to Upstash and Redis are architectural descriptions of the target system, not functional exfiltration vectors.
[EXTERNAL_DOWNLOADS]: No external packages or remote scripts are downloaded or executed by the skill instructions.

agent-signal