The Agent Skills Directory

[SAFE]: The skill instructions and configuration define a legitimate research workflow. No evidence of prompt injection, data exfiltration, or malicious code execution was found. The skill operates by reading documentation and writing summary files, which is consistent with its stated purpose. Analysis of the skill's data handling confirms it processes external sources (docs, code, specs) as intended for its primary function. While this presents an ingestion surface for external content, the risk is consistent with standard AI research tasks and no exploitable capability chains were identified.

research