The Agent Skills Directory

[SAFE]: The skill is purely informational, providing a framework for the agent to evaluate software engineering processes against established standards. It does not invoke any external tools, perform network requests, or execute scripts.
[INDIRECT_PROMPT_INJECTION]: The skill involves processing project-specific data (architecture descriptions, requirements) to populate a report template. While this presents a surface for indirect prompt injection if the project data contains malicious instructions, the skill lacks high-risk capabilities (like shell execution or network exfiltration) to exploit such an injection. The impact is limited to the accuracy of the generated report.

engineering-standards