Security audit
Security checks for vulnerabilities and agentic risk
This skill only adds a user-controlled coding workflow mode and does not show hidden, destructive, or data-stealing behavior.
Before installing, understand that enabling this mode will make the agent follow a more structured coding workflow until you turn it off. The only notable caveat is that the trigger examples are bilingual and could better state that equivalent wording is acceptable.
The description specifies explicit activation examples including Russian phrases, which embeds a language-specific interaction pattern. Because the file does not state that the skill is region-specific or that users may choose their preferred language, this is a natural-language locale policy concern under the stated rules.
The skill enumerates Russian and English trigger phrases, but does not clarify that users can interact in their chosen language or that these are non-exclusive examples. This can amount to an implicit language policy baked into the skill behavior without explicit justification.
No suspicious patterns detected.
