supply-chain-mgr
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external business data to perform calculations and generate supply chain reports, which creates a surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through user-provided inputs described in
SKILL.mdunder 'Step 1: รวบรวม context' (Business Context) and 'Step 2: ABC Analysis' (SKU lists and pricing). - Boundary markers: Absent. The instructions do not define specific delimiters or provide warnings for the agent to ignore instructions that might be embedded within the business data or SKU names provided by the user.
- Capability inventory: The skill primarily uses the agent's text generation and mathematical reasoning capabilities to produce markdown reports. It does not explicitly invoke high-risk tools like shell execution or network operations.
- Sanitization: No sanitization, validation, or filtering of the external business content is described in the skill's instructions.
Audit Metadata