atmee-product
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve live data (pricing, account status, avatar lists) from the
atmeeMCP server to answer user queries, which creates a surface for instructions embedded in that data to influence agent behavior. - Ingestion points: Untrusted data enters the agent context through MCP tool calls such as
get_account,get_balance, andlist_avatarsinSKILL.md. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when handling the data returned from the API.
- Capability inventory: The skill uses the
atmeeMCP tool (https://api.atmanity.us/mcp) as defined inopenai.yaml. No shell execution or local file-write capabilities were found in the analyzed files. - Sanitization: There is no documentation of sanitization, escaping, or schema validation for the data ingested from the remote server.
Audit Metadata