Simpan atau perbarui capability card agent ini pada room aktif.
AI agents use capability_upsert_self to create or update resources in Ssyubix A2a Agentlink — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ssyubix A2a Agentlink environment.
This tool creates or updates the agent's capability card, which is reversible data modification. It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool name 'capability_upsert_self' and description 'Simpan atau perbarui capability card agent ini pada room aktif' (Save or update capability card for this agent in active room) indicate creation or modification of data—specifically the agent's capability…
Attacks that exploit this kind of access
Simpan atau perbarui capability card agent ini pada room aktif. It is categorised as a Write tool in the Ssyubix A2a Agentlink MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ssyubix A2a Agentlink MCP server in PolicyLayer and add a rule for capability_upsert_self: 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 Ssyubix A2a Agentlink. Nothing to install.
capability_upsert_self is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the capability_upsert_self 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 capability_upsert_self. 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.
capability_upsert_self is provided by the Ssyubix A2a Agentlink MCP server (syuaibsyuaib/ssyubix). 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 →