Unlink skill from code artifact (removes reference relationship). WHAT: Removes the association between a skill and a code artifact. WHEN: When a skill-code artifact link is no longer relevant or was created in error. BEHAVIOR: Removes association between skill and code artifact. Safe to call eve...
AI agents use unlink_skill_from_code_artifact to create or update resources in Forgetful — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Forgetful environment.
This tool modifies data by removing a reference relationship (unlink), which is a write operation. However, it is low severity because: (1) it only removes metadata links, not actual data; (2) both the skill and code artifact objects persist; (3) the operation is explicitly described as safe and reversible; (4) the blast radius if misused by an AI agent is minimal—the underlying resources remain available and can be…
From the tool's definition Removes the association between a skill and a code artifact. The description explicitly states: 'Skill and code artifact remain intact.' This is a reversible modification of relationship metadata, not destructive deletion.
Documented attack patterns abuse exactly the kind of access unlink_skill_from_code_artifact gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgetful, and nothing reaches the server without passing your rules. This is the rule we recommend for unlink_skill_from_code_artifact:
{
"version": "1",
"default": "deny",
"tools": {
"unlink_skill_from_code_artifact": {
"limits": [
{
"counter": "unlink_skill_from_code_artifact_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}unlink_skill_from_code_artifact stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unlink skill from code artifact (removes reference relationship). WHAT: Removes the association between a skill and a code artifact. WHEN: When a skill-code artifact link is no longer relevant or was created in error. BEHAVIOR: Removes association between skill and code artifact. Safe to call even if link doesn't exist. Skill and code artifact remain intact. Args: skill_id: Skill ID to unlink code_artifact_id: Code artifact ID to unlink ctx: Context (automatically injected) Returns: Confirmation dict with success status Raises: ToolError: If unlinking fails. It is categorised as a Write tool in the Forgetful MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Forgetful MCP server in PolicyLayer and add a rule for unlink_skill_from_code_artifact: 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 Forgetful. Nothing to install.
unlink_skill_from_code_artifact 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 unlink_skill_from_code_artifact 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 unlink_skill_from_code_artifact. 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.
unlink_skill_from_code_artifact is provided by the Forgetful MCP server (scottrbk/forgetful). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
59 Forgetful tools catalogued and risk-classified — across an index of 42,500+ MCP servers.