T09 · Insecure Skill Coding Practices
- Location
xiaolongxia.py:103- Finding
Plaintext Conversation Retention and Repeated External Disclosure
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed DeepSeek coding-assistant skill that stores and resends conversation history, which is useful for its purpose but requires privacy caution.
Install only if you are comfortable with prompts, code, and prior conversation history being saved locally in plaintext and sent to DeepSeek on later requests. Clear history before discussing sensitive code, credentials, private logs, or regulated data.
xiaolongxia.py:103Plaintext Conversation Retention and Repeated External Disclosure
The skill explicitly states that it will automatically carry forward conversation history and send it to the DeepSeek API, but it does not provide a clear warning or consent mechanism about privacy implications. This can expose sensitive source code, credentials, internal discussions, or personal data from prior turns to an external service without meaningful user awareness.
The skill advertises capabilities that imply file access, local persistence, and outbound network access, but it does not declare any explicit tool scope or permissions boundary. This weakens least-privilege controls and makes it harder for users or the platform to understand and constrain what the skill can read, write, or transmit.
The trigger phrases are extremely broad and match common programming-related conversation, so the skill may activate in many contexts where the user did not intend to invoke an external coding assistant. Because the skill also sends prompts and history to a third-party API, accidental invocation can lead to unanticipated data exposure and overuse of privileged functionality.
The skill documents persistent storage of conversation history in a local file, but it does not warn users that sensitive prompts, code, secrets, or review content may be retained on disk. Local retention increases the chance of later disclosure through other users on the system, backups, malware, or unintended file access.
The system message is written entirely in Chinese and defines the assistant persona and output rules in Chinese, while the file contains no indication that users may choose another language. This creates a natural-language locale constraint without opt-in, which matches the language/locale policy violation category.
The description is written entirely in Chinese ("小龙虾-DeepSeek版超级编程助手") and does not indicate that users can choose another language or locale. Per the policy, forcing a specific language without opt-in is a natural-language policy violation.
The system prompt is entirely written in Chinese and defines the assistant persona and interaction rules in that locale, with no indication that the user can choose another language. This can violate language/locale policy when a skill imposes a specific language without opt-in or documented justification.
The skill persists full conversation history to a local file under the user's home directory without any notice, consent, retention policy, or access control hardening. Because this is a programming assistant, prompts may contain source code, secrets, tokens, internal URLs, or proprietary data, so silent storage materially increases privacy and secret-exposure risk on shared systems or if the account is later compromised.
The skill sends the entire message history, including prior user inputs, to the external DeepSeek API without an explicit warning or consent flow. In this skill's context, users are likely to paste code, logs, credentials, or confidential business data for debugging and review, so undisclosed third-party transmission can cause privacy, compliance, and secret-leak incidents.
The file contains natural-language text only in Chinese ('DeepSeek 官方 API 配置'), which reflects a fixed language choice with no indication that users can select a preferred language. The policy explicitly calls for flagging language or locale constraints when they are imposed without opt-in or documented justification.