AI agents call flaw_package_versions_list to retrieve information from Osidb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists package version information associated with a flaw identifier. It performs a query operation that returns data without side effects, matching the 'Read' category. The low severity reflects that querying vulnerability metadata poses minimal risk even if misused by an AI agent, as it only exposes information that is intended to be queryable.
From the tool's definition Tool name 'flaw_package_versions_list' and description 'Paginated package version rows for a flaw id' indicate data retrieval with pagination.
Attacks that exploit this kind of access
Paginated package version rows for a flaw id. It is categorised as a Read tool in the Osidb MCP Server, which means it retrieves data without modifying state.
Register the Osidb MCP server in PolicyLayer and add a rule for flaw_package_versions_list: 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 Osidb. Nothing to install.
flaw_package_versions_list 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 flaw_package_versions_list 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 flaw_package_versions_list. 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.
flaw_package_versions_list is provided by the Osidb MCP server (vdanen/osidb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →