The Agent Skills Directory

[SAFE]: The skill functions as a documentation and code research tool, utilizing platform-provided search interfaces. It does not possess any capabilities for modifying files, executing arbitrary shell commands, or accessing sensitive user data.
[SAFE]: No evidence of malicious patterns, such as direct prompt injection, credential exfiltration, or obfuscated content, was found within the skill's instructions or assets.
[SAFE]: All external tools and repository references are aligned with the official vendor (Equinor) and are used solely for information retrieval, consistent with the skill's stated purpose.
[SAFE]: Although the skill processes external search data which presents a surface for indirect prompt injection, the impact is negligible due to the absence of destructive capabilities like file writing or shell access.

fusion-research