agent-inbox
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated feedback which represents an attack surface for indirect prompt injection.
- Ingestion points: User feedback text is ingested via the
listAgentInboxItemsfunction inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters provided to isolate the feedback content from the agent's instructions.
- Capability inventory: The skill allows the agent to modify the state of feedback items using
updateAgentInboxIteminSKILL.md. - Sanitization: The instructions do not mention any validation or sanitization of the feedback text before processing.
Audit Metadata