The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is designed to guide the AI agent in rephrasing its previous output using Simplified Technical English (ASD-STE100) and terminology from local glossary files.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the conversation history and local files (GLOSSARY.md, GLOSSARY-MAP.md). However, the skill explicitly disables model invocation (disable-model-invocation: true), meaning it cannot call external tools or execute commands, which eliminates the risk of an injection attack resulting in unauthorized actions.
[DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or accesses to sensitive system paths detected. The referenced files are standard project documentation.

wait-what