# HiddenLayer MCP tool parameter abuse / prompt leak

- ID: hiddenlayer-mcp-param-abuse-2025
- Reported: 2025-05-01
- Researcher: HiddenLayer
- Organization: HiddenLayer
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/hiddenlayer-mcp-param-abuse-2025/
- Entry JSON: https://openattacks.ai/api/attacks/hiddenlayer-mcp-param-abuse-2025.json
- Browse title: HiddenLayer: MCP tool parameter abuse leaks prompts
- Editorial summary: Research showed malicious MCP tools with suggestive parameter names can trick models into filling in system prompts and chat history, which the tool then exfiltrates.
- Evidence class (catalog annotation): Research demonstration
- Source-stated target environments: Agents & MCP
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/hiddenlayer-mcp-param-abuse-2025.json

## Technique
Malicious MCP tool schemas use suggestive unused parameter names (system\_prompt, conversation\_history, chain\_of\_thought, tools\_list) so the model fills them with sensitive context; tool then exfiltrates via HTTP. Also showed fake function schemas in user prompts leaking system prompts/tools.

## Stack relevance (editorial)
Assessment: mapped. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
First action: Review tool parameter descriptions and prevent secrets or conversation content being passed to untrusted tools.
- Relationship: workflow; tools: no specific product; OS scope: not OS-specific / not stated; requires existing MCP connections: true.
  Relevance: The research uses MCP tool parameter names to solicit sensitive model context.
  Condition to check: An untrusted tool definition must be exposed to the model; the requested context must be available.
  Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
unknown

## AI tooling and models
- MCP tool schemas
- agent frameworks

## Other tooling
- unknown

## Victims and sectors
unknown

## Target geography
- unknown

## Attribution
unknown

## Scale and metrics
unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Connection prerequisite is unspecified [unknown]
The supplied entry does not document the initial route to the malicious tool.
Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse

### step-2: Tool schema requests sensitive context [ai]
Unused parameter names encourage the model to fill in prompts, history and tool information.
Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse

### step-3: Model passes context as arguments [execution]
Sensitive values are included in the tool invocation.
Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse

### step-4: Tool exfiltrates the arguments [impact]
The demonstrated tool sends the collected context through HTTP.
Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse

Connections:
- step-1 -> step-2
- step-2 -> step-3
- step-3 -> step-4

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### step-1: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- Qualification: The supplied account leaves this stage unestablished. Obtain a source-backed procedure before proposing a runtime query.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- No direct MagicSword prevention claim is recorded for this stage.

### step-4: Sensitive data → unusual destination
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/exfil.sigma.yml
- KQL query download: /api/detections/exfil.kql
- SPL query download: /api/detections/exfil.spl
- Hunt hypothesis: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
- Required telemetry: Sensitive resource access / DLP records; Proxy, egress and cloud upload events; Agent / SaaS audit with correlation IDs
- Investigate: Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Investigate: Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
- Limitation: An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0051.001: Indirect — Attacker-supplied tool schemas induce sensitive-context disclosure.
  Technique: https://atlas.mitre.org/techniques/AML.T0051.001
  Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse
- AML.T0056: Extract LLM System Prompt — The demonstration includes system-prompt extraction.
  Technique: https://atlas.mitre.org/techniques/AML.T0056
  Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse
- AML.T0086: Exfiltration via AI Agent Tool Invocation — Sensitive content is transmitted through tool parameters.
  Technique: https://atlas.mitre.org/techniques/AML.T0086
  Evidence: https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters ; https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse

## Defensive notes
Schema allowlists; strip unexpected params; never send full system prompt to tools

## Sources
- https://www.hiddenlayer.com/research/exploiting-mcp-tool-parameters
- https://hiddenlayer.com/innovation-hub/beyond-mcp-expanding-agentic-function-parameter-abuse
