Pilot Log Analytics Setup

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed log-analytics setup guide with expected local configuration and optional external reporting paths, not a malicious skill.

Before installing, review the child skills this setup installs, especially `pilot-webhook-bridge` and `pilot-slack-bridge`. Only use Slack channels or webhook destinations you control, redact secrets and personal data from logs and reports, and check whether `~/.pilot/setups/log-analytics.json` already exists before running the manifest step.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The dashboard role is documented as a visualization/search component, but it is also granted outbound webhook and Slack bridging capabilities that can transmit derived log data outside the local analytics pipeline. In a log analytics context, this increases data exfiltration and privacy risk because reports and alerts may contain sensitive operational details, yet the skill provides no explicit approval gate, destination validation, or data minimization guidance.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The dashboard host is assigned skills for webhook forwarding and Slack posting even though the stated purpose is search, visualization, and reporting. This violates least privilege for a visualization node and expands the attack surface by enabling external communications that are not strictly necessary for core dashboard operation.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README explicitly routes log reports to external dashboards and Slack channels but provides no warning, scoping guidance, or sanitization requirements for potentially sensitive log contents. In a log analytics skill, logs commonly contain secrets, tokens, internal hostnames, stack traces, and user data, so encouraging external forwarding without guardrails materially increases the risk of unintended data disclosure.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill instructs the agent to create and overwrite a persistent configuration file under ~/.pilot/setups without warning the user that local state will be modified. Persistent writes can silently alter future agent behavior, overwrite existing setup definitions, or leave behind configuration that the user did not intend to keep.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill describes forwarding reports to external dashboards and Slack channels but does not warn that log-derived data may leave the local environment. In observability setups, even summaries and alerts can contain sensitive infrastructure names, error details, or incident context, so omission of a privacy warning materially increases the risk of unintentional data disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.