Fulcra Morning Briefing

• Outcome: Review
• Latest audit: Jul 10, 2026 · 3:01 AM UTC
• Version: 1.1.10

Overview

This morning-briefing skill has a coherent purpose, but it handles sensitive personal context and appears to send location data to a third-party weather service without enough disclosure or user control.

Review this skill before installing. It may read sensitive sleep, health, calendar, wearable, and location context, and the supplied code evidence shows location may be sent to wttr.in for weather. Install only if you are comfortable with that data use, and prefer a version that clearly declares shell/network requirements, limits the Fulcra command path, and makes weather lookup opt-in.

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
• Rogue Agent: Self-Modification, Session Persistence
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Taint Tracking: Direct Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain

Findings (8)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def run_fulcra_json(*args: str) -> Any:
    command = os.environ.get("FULCRA_CLI_COMMAND", "uv tool run fulcra-api").split()
    result = subprocess.run(
        [*command, *args],
        capture_output=True,
        text=True,

• Confidence: 95% confidence
• Finding: result = subprocess.run( [*command, *args], capture_output=True, text=True, timeout=60, check=False, )

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def get_weather(location: str) -> dict[str, Any]:
    try:
        result = subprocess.run(
            ["curl", "-s", f"wttr.in/{location}?format=%l:+%c+%t+%h+%w"],
            capture_output=True,
            text=True,

• Confidence: 84% confidence
• Finding: result = subprocess.run( ["curl", "-s", f"wttr.in/{location}?format=%l:+%c+%t+%h+%w"], capture_output=True, text=True, timeout=10, c

Tainted flow: 'command' from os.environ.get (line 48, credential/environment) → subprocess.run (code execution)

Medium

• Category: Data Flow

Content

def run_fulcra_json(*args: str) -> Any:
    command = os.environ.get("FULCRA_CLI_COMMAND", "uv tool run fulcra-api").split()
    result = subprocess.run(
        [*command, *args],
        capture_output=True,
        text=True,

• Confidence: 98% confidence
• Finding: result = subprocess.run( [*command, *args], capture_output=True, text=True, timeout=60, check=False, )

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill instructs the agent to execute shell commands and use environment-based configuration, but the skill metadata shown does not declare corresponding permissions. That mismatch is dangerous because it can lead to undeclared command execution and access to local context or external services without clear user review.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The skill description centers on Fulcra-context-based briefing generation, but this function performs an unrelated external weather lookup. That broadens data exposure and network behavior beyond the stated local/personal-context purpose, which is risky in privacy-sensitive agent skills. The mismatch between declared purpose and actual external behavior makes the capability more dangerous, not less.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README explicitly promotes access to highly sensitive data categories including sleep, heart rate, HRV, location, and calendar context, but it does not present a clear, prominent privacy disclosure describing exactly what data will be collected, where it will be stored or transmitted, retention expectations, or how users should consent before use. In a skill designed for agents to assemble personalized briefings, this omission increases the risk of over-collection or unexpected handling of health and location data by downstream users or integrators.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The function sends the user's location string to wttr.in without any user-facing warning, consent, or privacy notice. Location can be sensitive personal data, and this creates a silent third-party disclosure channel from a morning-briefing skill that also processes sleep, biometrics, and calendar context. In this skill context, undisclosed outbound transmission is materially risky.

Session Persistence

Medium

• Category: Rogue Agent

Content

Deliver a personalized morning briefing calibrated to how the human actually slept. Bad night? Keep it short and gentle. Great sleep? Go deep on the day ahead.

This is the lightweight morning workflow on top of **[fulcra-context](../fulcra-context/SKILL.md)**. Fulcra gives agents and their humans scoped, secure access to read and write real-world context and shared human/agent memory: attention, events, location, calendar, health, wearables, and other streams.

## What You'll Compose

• Confidence: 78% confidence
• Finding: write real-world context and shared human/agent memory: attention, events, location, calendar, health, wearables, and other streams. ## What You'll Compose A morning briefing that includes: - **Slee

VirusTotal

60/60 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.