Back to skill

Security audit

BP Log Sentinel

Security checks for vulnerabilities and agentic risk

Overview

This skill locally analyzes user-supplied blood-pressure logs and does not show hidden data access, persistence, network use, or privilege-seeking behavior.

Install only if you are comfortable giving the skill local access to the blood-pressure CSV you choose to analyze. Treat its output as informational support for adult home logs, not a diagnosis or medication plan, and seek urgent care for high readings with symptoms as the skill itself advises.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

Lines L45-L48 state that the tool's report is formatted to include the averaging note, the average ± SD, and the morning/evening split. In this file, however, there is no implementation code or even executable specification for computing those values—only descriptive prose—so the documentation overstates what this artifact itself does.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The report text tells users to bring the log to 'your physician,' which hard-codes a specific clinician term and may not fit all locales or healthcare systems. This is a natural-language locale/policy issue because the skill does not offer a neutral alternative such as clinician, doctor, or healthcare professional.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.