Security audit
Security checks for vulnerabilities and agentic risk
This sleep-coaching skill is mostly coherent, but it can automatically read and update persistent personal sleep records from broad triggers without a clear consent or review step.
Install only if you are comfortable with the agent keeping a persistent local sleep log. Before using it, consider narrowing activation to explicit sleep-tracking requests and requiring confirmation before any write to `knowledge/personal/sleep.md`.
The trigger list is overly broad for a personal-data-handling skill, including everyday terms like 'tired', 'fatigue', 'rest', and 'alarm' that can appear in many unrelated conversations. This can cause the skill to activate outside clear sleep-tracking intent and then read or update personal sleep memory unexpectedly, increasing privacy and integrity risk.
The operational instructions and user-facing guidance are written in Russian, which implies a fixed language/locale for the skill. The file does not indicate that the user can choose another language or that the Russian-only behavior is required for a documented regional purpose.
The skill instructs the agent to update a persistent personal file whenever the user mentions sleep data, but it provides no disclosure, consent flow, or confirmation before modifying stored personal information. In a personal-health-adjacent context, silent persistence of behavioral data can violate user expectations and lead to unauthorized retention or corruption of sensitive history.
No suspicious patterns detected.
