Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed horoscope and astrology helper with limited local data reads and a named external horoscope/MCP integration, with privacy and CLI-behavior caveats but no evidence of malicious behavior.
Install only if you are comfortable using a Chinese-language astrology skill and, for taibu MCP features, sharing birth date/time details with the configured MCP provider. The local scripts are simple and do not persist data, but the documented command examples may not behave as written because the scripts contain test harnesses instead of argument parsing.
This description-behavior mismatch becomes security-relevant because the skill declares benign horoscope functionality while also indicating external network access without corresponding permission disclosure. Misleading capability descriptions can prevent informed consent and proper security review, especially when user birth/date information may be sent to third-party services.
This description-behavior mismatch becomes security-relevant because the skill declares benign horoscope functionality while also indicating external network access without corresponding permission disclosure. Misleading capability descriptions can prevent informed consent and proper security review, especially when user birth/date information may be sent to third-party services.
This description-behavior mismatch becomes security-relevant because the skill declares benign horoscope functionality while also indicating external network access without corresponding permission disclosure. Misleading capability descriptions can prevent informed consent and proper security review, especially when user birth/date information may be sent to third-party services.
The skill advertises network access to the ohmanda API and local file reads, but the manifest shown in SKILL.md does not declare any explicit tool scope such as permissions or allowed-tools. This creates a least-privilege and review gap: users and the hosting platform cannot clearly see what capabilities the skill expects, increasing the risk of unintended data access or outbound requests.
The examples invite users to provide birth dates, times, and related personal information for horoscope and fate-analysis queries, but the skill description does not warn that such data may be sent to external services. This undermines informed consent and can expose sensitive personal data to third parties, especially for tools like bazi or astrology that often require precise birth details.
This JSON contains user-facing natural-language content exclusively in Chinese across traits, advice, and descriptions. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the constraint is explicitly documented and justified, which is not present in this file.
The skill description, examples, and invocation guidance are entirely in Chinese and explicitly frame the interaction around Chinese-language prompts, without noting any user language choice or opt-in. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
This JSON file stores all user-facing summaries, strengths, conflicts, and advice in Chinese, with no indication that the skill supports other languages or that Chinese is an intentional region-specific constraint. Under the language/locale policy rule, a skill that effectively forces one language without user opt-in or justification is a natural-language policy concern.
This manifest-style data file hardcodes Chinese-language field values such as zodiac names, elements, colors, and weekdays throughout the dataset. Because SQP-3 applies to all file types and flags language/locale constraints without user opt-in or documented justification, the file presents a language-specific output policy concern.
This Python file contains natural-language descriptions in the module docstring that fix the skill's language to Chinese. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation, and there is no indication here that the skill is intentionally region-specific or that users can choose another language.
This code presents its description, comments, error messages, and printed output exclusively in Chinese. Under the policy rule, forcing a specific language without offering a user choice can be a natural-language policy violation.
This code presents its purpose and output exclusively in Chinese, and the same locale choice continues throughout comments and printed messages. Under the policy, forcing a specific language without offering a choice can be a natural-language policy violation.
