launch
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or persistence mechanisms were detected in the skill instructions or metadata.
- [PROMPT_INJECTION]: The skill is designed to ingest project context from local files such as '.agents/product-marketing.md' to customize its advice. This constitutes a surface for indirect prompt injection. However, the risk is negligible as the skill lacks access to dangerous tools or shell commands and only provides text-based marketing responses in Russian.
- Ingestion points: Reads '.agents/product-marketing.md', '.claude/product-marketing.md', and 'product-marketing-context.md'.
- Boundary markers: No explicit delimiters or warnings are used for the ingested content.
- Capability inventory: Limited to generating marketing frameworks and launch checklists in Russian.
- Sanitization: No input validation or sanitization is performed on the ingested context files.
Audit Metadata