baby-fever-triage

• Outcome: Pass
• Latest audit: Sep 27, 2026 · 3:33 PM UTC
• Version: 1.0.0

Overview

This skill is a local pediatric fever decision-support tool whose sensitive fever log storage is disclosed and purpose-aligned, with no evidence of hidden access, exfiltration, or persistence beyond the user-created log file.

Install only if you are comfortable keeping a child fever log as a local JSON file. Use it as informational support, keep fever.json in a private directory on shared machines, delete it when no longer needed, and do not let the tool replace emergency services or a clinician's advice.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence

Finding

The skill describes persistent local state in fever.json and therefore implies file read/write capability, but it does not explicitly declare any tool scope such as permissions or allowed-tools. That mismatch weakens least-privilege guarantees and can cause the host agent to grant broader filesystem access than users expect, which is more sensitive here because the data includes child health notes, temperatures, and medication logs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The tool stores sensitive child health information in a predictable local file (fever.json in the current working directory, or an arbitrary --db path) without an explicit disclosure at logging time, consent prompt, or any filesystem permission hardening. In a medical-triage context, temperature history, medication doses, symptoms, and notes are health data; on multi-user systems or shared directories this creates a realistic confidentiality risk through unintended exposure.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low

• Category: Dangerous Code Execution
• Confidence: 50% confidence

Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/fever.py (reported line 158)May include surrounding context.

python

# 2) RED FLAGS
# ----------------------------------------------------------------------------
def cmd_flags(a):
    present = [k for k, _ in RED_FLAGS if getattr(a, k.replace("-", "_"), None)]
    print("Red-flag checklist (any YES = EMERGENCY-NOW regardless of age/temperature):\n")
    for k, desc in RED_FLAGS:
        v = getattr(a, k.replace("-", "_"), None)

Dynamic attribute access via getattr()

Low

• Category: Dangerous Code Execution
• Confidence: 50% confidence

Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/fever.py (reported line 161)May include surrounding context.

python

present = [k for k, _ in RED_FLAGS if getattr(a, k.replace("-", "_"), None)]
    print("Red-flag checklist (any YES = EMERGENCY-NOW regardless of age/temperature):\n")
    for k, desc in RED_FLAGS:
        v = getattr(a, k.replace("-", "_"), None)
        mark = "YES" if v else ("no" if v is False else "? ")
        print(f"  [{mark:>3}] {k:22} {desc}")
    print()

Static analysis

No suspicious patterns detected.