The Agent Skills Directory

[SAFE]: No security issues detected. Analysis of the skill's logic, tool usage, and data handling confirms behavior consistent with its stated purpose of knowledge synthesis.- [EXTERNAL_DOWNLOADS]: The skill uses the mcp__web-reader__webReader tool to retrieve content from user-specified URLs. This is a functional requirement for analyzing external articles or documentation as part of the forging process.- [COMMAND_EXECUTION]: All operations are performed using platform-provided tools (Read, Write, Agent). No arbitrary shell commands, risky subprocess calls, or external script execution were found.- [PROMPT_INJECTION]: The skill defines clear operational boundaries and logic for its mapping methodology. It does not contain instructions to bypass safety guidelines, reveal system prompts, or override agent constraints.

forge