T09 · Insecure Skill Coding Practices
- Location
SKILL.md:11- Finding
Unprotected Persistence of Potentially Sensitive Session Data
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is for saving and restoring sessions, but it automatically persists conversation history and context without enough controls over sensitive data.
Review this carefully before installing. It may be useful if you want resumable sessions, but you should only enable it where stored snapshots are protected, redacted, easy to delete, and restored only after explicit confirmation. Avoid using it in sessions that may contain credentials, personal data, or confidential workspace details unless those controls exist.
SKILL.md:11Unprotected Persistence of Potentially Sensitive Session Data
The skill states that it periodically saves conversation history, tasks, and context every 30 minutes, but it does not warn users that potentially sensitive data will be persisted. This creates a privacy and data-handling risk because users may disclose secrets, personal information, or workspace context without informed consent, while the skill automatically stores that information.
The user-facing description and instructions are presented entirely in Chinese, with no indication that the user can choose another language or that the skill is region-specific. This can violate language or locale policy when a skill imposes a specific language without user opt-in.
The manual trigger phrase "用户说'保存快照'" is broad and lacks explicit activation boundaries, confirmation, or anti-spoofing constraints. In a conversational system, ambiguous triggers can cause unintended snapshot saves when the phrase appears in quoted text, examples, or adversarial prompt content, leading to unnecessary capture of conversation and context data.
The restore section describes loading the latest snapshot and restoring conversation context without warning that restored state may contain stale, incorrect, or sensitive information from earlier interactions. Reintroducing such context can confuse later decisions, revive expired secrets, or expose prior user data in a new conversational state.
The restore flow uses inconsistent phrases ("恢复上一个快照" vs. later "恢复快照") and does not specify authorization, recency checks, or confirmation before loading prior state. This can allow accidental or malicious reintroduction of stale context, causing the agent to act on outdated assumptions or re-expose previously stored sensitive information.