Синхронизирует встроенные agent skills в ~/.agents/skills.
AI agents use install_agent_skills to create or update resources in Booster MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Booster MCP environment.
This tool synchronizes/installs agent skills into a local directory, which constitutes creating or modifying files. This is a Write operation rather than Execute because it appears to perform data synchronization rather than running arbitrary code. Severity is medium because modifying ~/.agents/skills could alter agent behavior but is limited to a single directory and is likely reversible.
From the tool's definition Tool description states 'Синхронизирует встроенные agent skills в ~/.agents/skills' (Synchronizes built-in agent skills in ~/.agents/skills), indicating file creation or modification in a user directory.
Attacks that exploit this kind of access
Синхронизирует встроенные agent skills в ~/.agents/skills. It is categorised as a Write tool in the Booster MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Booster MCP server in PolicyLayer and add a rule for install_agent_skills: 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 Booster MCP. Nothing to install.
install_agent_skills 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 install_agent_skills 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 install_agent_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.
install_agent_skills is provided by the Booster MCP server (neuroghostdev/booster_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 →