ONLY FOR SALESFORCE B2C COMMERCE (SFCC) PROJECTS. IMPORTANT: Before calling this tool, ALWAYS ASK THE USER if they want to install AGENTS.md and bundled SFCC skills into their project. If the user declines, do NOT call this tool - instead call disable_agent_sync to permanently disable this sugges...
AI agents use sync_agent_instructions to create or update resources in Sfcc Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sfcc Dev environment.
This tool writes files into the project directory by installing and merging AGENTS.md and skill files. It modifies the project structure, which is a Write operation. Severity is high because it can overwrite or alter project-level agent configuration files across multiple potential skill directories, and misuse could inject malicious instructions into agent configuration files that govern AI behavior.
From the tool's definition installs/merges AGENTS.md and bundled SFCC skills into the project
Attacks that exploit this kind of access
ONLY FOR SALESFORCE B2C COMMERCE (SFCC) PROJECTS. IMPORTANT: Before calling this tool, ALWAYS ASK THE USER if they want to install AGENTS.md and bundled SFCC skills into their project. If the user declines, do NOT call this tool - instead call disable_agent_sync to permanently disable this suggestion. This tool installs/merges AGENTS.md and bundled SFCC skills into the project (or a temp dir for manual merge). Supports dry-run planning, append/replace/skip merge strategies, and selecting skills directory (.github/skills, .agents/skills, .claude/skills, .agent/skills, .cursor/skills, and user-home defaults like ~/.copilot/skills). It is categorised as a Write tool in the Sfcc Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sfcc Dev MCP server in PolicyLayer and add a rule for sync_agent_instructions: 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 Sfcc Dev. Nothing to install.
sync_agent_instructions 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 sync_agent_instructions 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 sync_agent_instructions. 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.
sync_agent_instructions is provided by the Sfcc Dev MCP server (sfcc-dev-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 →