Freshdesk

ReviewAudited by ClawScan on May 10, 2026.

Overview

This appears to be a real Freshdesk integration, but it can change or delete customer support data through Membrane without clear approval safeguards in the artifacts.

Install only if you are comfortable using Membrane as the bridge to Freshdesk. Use a least-privilege Freshdesk account, confirm the tenant and connection ID, and require explicit approval before the agent creates, updates, or deletes tickets, contacts, companies, agents, groups, or other Freshdesk records.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

ConcernMedium Confidence
ASI02: Tool Misuse and Exploitation
What this means

If the agent misunderstands a request or acts too broadly, it could modify or delete Freshdesk tickets, contacts, or related business records.

Why it was flagged

The documented Freshdesk actions include creating, updating, and deleting support/customer records, but the artifacts do not specify confirmation or scoping requirements before high-impact changes.

Skill content
Create Ticket ... Update Ticket ... Delete Ticket ... Delete Contact
Recommendation

Require explicit user confirmation before create, update, or delete actions; show the connection, target record IDs, and intended changes before execution; use a least-privilege Freshdesk account where possible.

NoteHigh Confidence
ASI01: Agent Goal Hijack
What this means

A returned instruction could steer the agent's workflow if treated as authoritative.

Why it was flagged

The skill allows remote service responses to provide procedural instructions to the agent, which is useful for setup but should not override the user's goal or safety constraints.

Skill content
`clientAction.agentInstructions` (optional) — instructions for the AI agent on how to proceed programmatically.
Recommendation

Treat remote `agentInstructions` as untrusted guidance: follow them only when they align with the user's request and do not bypass confirmations or security policy.

What this means

The agent's effective Freshdesk access will match the privileges granted through Membrane and the connected Freshdesk account.

Why it was flagged

The integration depends on delegated account authentication and credential refresh, which is expected for Freshdesk access but gives the connected account's privileges to the workflow.

Skill content
Membrane handles authentication and credentials refresh automatically
Recommendation

Connect only the intended Freshdesk account, prefer least-privilege roles, and revoke the Membrane connection when no longer needed.

What this means

Installing the CLI changes the local environment and runs code from the npm package distribution.

Why it was flagged

The skill asks for a global npm install using the moving `latest` tag; this is purpose-aligned but leaves behavior dependent on the currently published package version.

Skill content
npm install -g @membranehq/cli@latest
Recommendation

Install from the trusted package source, consider pinning a reviewed version, and use an isolated environment if possible.

What this means

Freshdesk tickets, contacts, and related customer data may be processed through the Membrane service during use.

Why it was flagged

Freshdesk access is mediated through Membrane, so the data and credential boundary includes that third-party service as well as Freshdesk.

Skill content
This skill uses the Membrane CLI to interact with Freshdesk. Membrane handles authentication and credentials refresh automatically
Recommendation

Verify the Membrane tenant, privacy expectations, and Freshdesk connection before using the skill with sensitive customer data.