The Agent Skills Directory

[SAFE]: No security issues were identified in this skill. The instructions and metadata are consistent with its stated purpose of code impact analysis.
[COMMAND_EXECUTION]: The skill references a specific tool, /sourceatlas:impact, to perform its analysis. This is a scoped tool call rather than arbitrary shell command execution.
[INDIRECT_PROMPT_INJECTION]: The skill interpolates user-provided strings (file paths or component names) into the analysis tool call. This represents a minimal attack surface typical for command-oriented skills and lacks dangerous capabilities like network access or file writes based on that input.

impact-analyzer