Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent local memory skill, but it should be reviewed because it requests shell execution while saying no shell execution is needed and it can create persistent conversation-derived records.
Review before installing. The skill is not showing exfiltration or destructive behavior, but users should be comfortable with persistent local memory in ~/evolution-engine/ and should remove or tightly scope exec access unless the publisher documents exactly why it is needed.
The trigger keywords are broad terms such as reflection, learning, and self-improving that can match ordinary conversation. This can cause the skill to activate unexpectedly in unrelated contexts, leading to unsolicited persistent memory behavior and increased exposure to prompt-driven side effects.
The skill describes persistent storage under ~/evolution-engine/ but does not provide a prominent warning or consent model before writing local files. Users may unknowingly cause long-lived storage of conversation-derived preferences, corrections, or project details, creating privacy and data governance risks.
The skill metadata exposes the exec tool while the documentation states the skill is pure Markdown and does not require exec. This mismatch can mislead users and reviewers about the skill’s actual capabilities, increasing the chance that an agent may invoke shell execution unnecessarily or that risky behavior escapes scrutiny.
The display name, summary, description, and trigger guidance are presented in Chinese, and the document does not indicate that language is selectable or that the skill is intentionally limited to Chinese-speaking users. This can conflict with language/locale policy expectations when a skill implicitly enforces one language without user opt-in.
No suspicious patterns detected.
