adb_permission_audit
Audit runtime permission grants for a package. Lists all granted dangerous permissions grouped by category (Camera, Location, Phone, SMS, etc.) and flags potentially over-provisioned permissions. Compares grants against the dangerous permission manifest to identify unnecessary access.
This record as markdown: /tools/io-github-fullread-deepadb/adb-permission-audit.md
What adb_permission_audit does on Deepadb
AI agents call adb_permission_audit to retrieve information from Deepadb without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why adb_permission_audit is rated Low
This is a diagnostic and auditing tool that retrieves and analyzes permission metadata on an Android device. It does not grant, revoke, or modify permissions; it only reads and reports on the current state. The blast radius from misuse is low—an attacker could learn which permissions an app has requested, but cannot escalate privileges or cause harm through this tool alone. Classification: Read.
From the tool's definition The tool 'audit[s] runtime permission grants' and 'lists all granted dangerous permissions' — these are query/inspection operations with no side effects.
Attacks that exploit this kind of access
The rule that runs adb_permission_audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Deepadb, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For adb_permission_audit, this is the rule to start with:
adb_permission_audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Deepadb, apply this rule, and every adb_permission_audit call is checked against it from then on.
Questions about adb_permission_audit
Audit runtime permission grants for a package. Lists all granted dangerous permissions grouped by category (Camera, Location, Phone, SMS, etc.) and flags potentially over-provisioned permissions. Compares grants against the dangerous permission manifest to identify unnecessary access. It is categorised as a Read tool in the Deepadb MCP Server, which means it retrieves data without modifying state.
Register the Deepadb MCP server in PolicyLayer and add a rule for adb_permission_audit: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Deepadb. Nothing to install.
adb_permission_audit is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the adb_permission_audit rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for adb_permission_audit. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
adb_permission_audit is provided by the Deepadb MCP server (deepadb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deepadb, and thousands of servers like it.
This server
Across the catalogue