4 results · Clear filters · Feed
-
Medium 5.3
AshAi sends unrecognized tool errors verbatim to MCP clients and the model, disclosing internal details
Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai allows a caller of an AshAi tool to read internal error details, including module names and data values, by making a tool call fail. AshAi.ToToolError gained an i…
-
Medium 6.0
AshAi aggregate tool can read field-policy-protected fields
AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type (min, max, sum, avg) that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields…
-
Medium 5.3
AshAi echoes raw tool exception messages into the conversation, disclosing internal details
Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai discloses internal error text to chat users. In AshAi.ToolLoop and AshAi.Tools, an exception raised while executing a tool was serialized verbatim with Exception.…
-
Medium 6.0
AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests. AshAi.ToolLoop classifies a model response of :t…