Load the full markdown content of a built-in skill. AI should follow the skill instructions after loading. Returns the SKILL.md body plus dependency / related skill names.
AI agents call harness_load_skill to retrieve information from Harness Engineering MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns existing skill documentation and metadata. It is a read-only operation that queries built-in skill resources without creating, modifying, executing external code, deleting data, or committing financial obligations. The returned markdown guides AI behavior but does not itself execute commands or trigger external side effects.
From the tool's definition Tool description explicitly states it 'Load[s] the full markdown content' and 'Returns the SKILL.md body plus dependency / related skill names' — pure retrieval with no side effects.
Attacks that exploit this kind of access
Load the full markdown content of a built-in skill. AI should follow the skill instructions after loading. Returns the SKILL.md body plus dependency / related skill names. It is categorised as a Read tool in the Harness Engineering MCP MCP Server, which means it retrieves data without modifying state.
Register the Harness Engineering MCP server in PolicyLayer and add a rule for harness_load_skill: 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 Harness Engineering MCP. Nothing to install.
harness_load_skill 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 harness_load_skill 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 harness_load_skill. 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.
harness_load_skill is provided by the Harness Engineering MCP server (movebrickschi/harness-engineering-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 →