docs-rules
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown-based instructional content. No executable scripts, binaries, or configuration files were found across the analyzed files.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for the agent to ingest external artifacts (code, requirements) to produce documentation. While this technically constitutes an ingestion surface for indirect prompt injection, the skill does not request or utilize any high-risk capabilities (such as network access or arbitrary command execution) that would facilitate exploitation. The instructions are focused on structured documentation generation within specific project directories.
- [OBFUSCATION]: The Cyrillic characters used in the validation rules (rules/validation.md) were evaluated for homoglyph attacks. The text consists of legitimate, fully Cyrillic words ('Поле', 'Правило', 'Ошибка') corresponding to the author's context and does not involve script-mixing to imitate Latin targets.
Audit Metadata