Manage agent skills. Actions: list (show skill index), bind (attach skill to agent), unbind (remove skill from agent), build (create skills from gap suggestions), develop (generate skill from ATI competency data).
Accepts raw HTML/template content (skills[].content); High parameter count (11 properties)
Part of the Gossipcat MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call gossip_skills to permanently remove or destroy resources in Gossipcat. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call gossip_skills in a loop, permanently destroying resources in Gossipcat. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
gossip_skills:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Gossipcat policy for all 21 tools.
Agents calling destructive-class tools like gossip_skills have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
gossip_skills is one of the critical-risk operations in Gossipcat. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Manage agent skills. Actions: list (show skill index), bind (attach skill to agent), unbind (remove skill from agent), build (create skills from gap suggestions), develop (generate skill from ATI competency data).. It is categorised as a Destructive tool in the Gossipcat MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for gossip_skills. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Gossipcat MCP server.
gossip_skills is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the gossip_skills rule in your Intercept 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 Intercept policy for gossip_skills. 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.
gossip_skills is provided by the Gossipcat MCP server (gossipcat). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept