ship-hero
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Prompt Injection (HIGH): The skill exhibits a significant Indirect Prompt Injection surface. It facilitates the ingestion of external content (orders, products, notes) from the ShipHero API and grants the agent the capability to execute state-changing mutations based on that data.
- Ingestion points: GraphQL query results in
references/graphql-operations.mdandSKILL.md. - Boundary markers: There are no instructions or delimiters defined to prevent the agent from following malicious instructions potentially embedded in order notes or product fields.
- Capability inventory: High-privilege write operations including
order_update,inventory_add, andwebhook_createacross all reference files. - Sanitization: No sanitization or validation logic is present in the provided Python or Node.js integration examples.
Recommendations
- AI detected serious security threats
Audit Metadata