chinese-lottery-predict
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill repository contains only Markdown instruction and documentation files (SKILL.md, README.md, CHANGELOG.md, and references/data-sources.md). No executable scripts, binaries, or source code files are included.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: External data enters the agent context through WebSearch, WebFetch, duckducksearch, and tavily-search tools (defined in SKILL.md and references/data-sources.md). Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions embedded in fetched web content. Capability inventory: The skill uses platform-provided network search tools. No subprocess calls, file-write operations, or dynamic code execution are defined in the repository. Sanitization: Validation rules in references/data-sources.md cover data integrity (range, count, and uniqueness of lottery numbers), but no sanitization or filtering of natural language content from external sources is provided.
Audit Metadata