FTTR Operator Copilot

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This appears to be a coherent FTTRAI operator API client, but it uses a sensitive operator token and can perform limited provider-side actions such as marking alerts read.

Before installing, confirm that this agent is allowed to use an FTTRAI operator token and view managed-device/network data. Use a least-privileged token, keep FTTRAI_RPC_URL on a trusted HTTPS endpoint, and require confirmation before marking alerts as read or running real-time device query commands.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

What this means

The agent can query operator-visible managed devices, alerts, topology, metrics, and diagnostics using the supplied token.

Why it was flagged

The skill requires a bearer token that delegates operator API access to the agent; this is expected for the integration but gives the agent access to whatever devices and regions the token can reach.

Skill content
FTTRAI_OPERATOR_AUTH_TOKEN ... Operator bearer token used to call FTTRAI operator APIs. ... Operator tools are scoped by the token user's region and permissions.
Recommendation

Use a least-privileged operator token, keep it out of chat/logs, rotate it if exposed, and install this only in an environment where the agent is allowed to view FTTRAI operator data.

What this means

If invoked unintentionally, an alert could be marked read or a device query command could be sent under the operator identity.

Why it was flagged

The skill includes a provider-side state change and device query command dispatch, but these capabilities are disclosed, scoped to alert IDs or device identifiers, and aligned with the operator workflow.

Skill content
`mark_alerts_as_read`: Mark alert IDs as read. This writes to FTTRAI state. ... `mark_alerts_as_read` writes state; confirm intent before using it. ... Real-time command tools send device query commands
Recommendation

Require explicit user confirmation before marking alerts read, and use real-time command tools only for devices the operator is authorized to inspect.

What this means

A misconfigured endpoint could send the operator token and FTTRAI requests somewhere unsafe.

Why it was flagged

The configurable RPC base URL accepts both HTTP and HTTPS; because authenticated RPC calls use this base URL, setting it to an untrusted or plaintext HTTP endpoint could expose the bearer token.

Skill content
if (!["http:", "https:"].includes(parsedUrl.protocol)) { ... FTTRAI_RPC_URL 只支持 http 或 https
Recommendation

Leave the default HTTPS endpoint unless you have a trusted FTTRAI backend, and avoid plain HTTP for bearer-token traffic.