commerce-integrated-strategy
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process untrusted external data.
- Ingestion points: The skill explicitly requests and processes user-provided dashboard screenshots, CSV/Excel report exports from external commerce platforms (Naver, Coupang), and outputs from preceding workflow skills (
SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions to isolate user-provided data from the agent's core instructions.
- Capability inventory: The skill generates comprehensive strategy reports, creates JSON structures for macro strategies, and performs automatic chaining to the
moai-core:ai-slop-reviewerskill (SKILL.md). - Sanitization: There is no evidence of content sanitization or validation for the data ingested from external sources.
- [SAFE]: All external URL references in the documentation point to well-known Korean e-commerce management services such as ShopManager, EasySeller, and Sabangnet (
references/channel-mix.md). - [SAFE]: The skill uses automatic chaining to vendor-specific tools (e.g.,
moai-core:ai-slop-reviewer) which is consistent with the provided author context for 'modu-ai' (SKILL.md).
Audit Metadata