The Agent Skills Directory

[SAFE]: The skill provides instructional methodology for cyber threat intelligence analysis. No patterns associated with data exfiltration, credential harvesting, or unauthorized command execution were detected.
[NO_CODE]: The skill is comprised solely of Markdown instructions and a CSV template. There are no scripts, binaries, or references to external package managers (pip, npm) within the skill files.
[PROMPT_INJECTION]: The skill is designed to analyze untrusted external content, which inherently presents an indirect prompt injection surface. However, the skill provides a structured workflow for objective analysis and lacks any exploitable capabilities (such as file-system writes or network tools) that could be leveraged by malicious input data. The instructions do not attempt to override agent safety guidelines or system constraints.

admiralty-system