Security audit

hydration-hero

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local hydration-tracking CLI, but users should treat its personalized hydration advice as general wellness guidance rather than medical advice.

Install only if you are comfortable storing hydration, weight, schedule, caffeine/alcohol, and related wellness data in a local file at ~/.hydration_hero.json. Treat targets, schedules, and urine-color guidance as general wellness estimates, not medical advice, especially if you are pregnant, have kidney/heart/electrolyte issues, take relevant medications, have fluid restrictions, or have concerning symptoms.

A.I.G

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

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (6)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The README presents hydration calculations as exact, personalized guidance and even says it calculates the user's 'exact need' without clearly warning that the output is general wellness information rather than medical advice. Users with kidney, heart, endocrine, pregnancy, pediatric, or other health considerations could rely on these recommendations inappropriately, leading to under- or over-hydration decisions.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill describes local file read/write behavior by storing user data in ~/.hydration_hero.json, but it does not declare any explicit tool scope or permissions. In an agent ecosystem, undeclared filesystem access weakens transparency and policy enforcement, and could allow broader-than-expected file interactions if the implementation is later expanded or misused.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file gives concrete, prescriptive hydration instructions for exercise, hot climates, caffeine, alcohol, and bedtime rehydration without clear medical disclaimers that fluid needs vary by body size, medications, kidney/heart conditions, pregnancy, age, and environment. In a skill explicitly designed to calculate personalized intake and generate schedules, users may treat this as health guidance; for some users, following fixed advice could contribute to overhydration, delayed care, or unsafe intake patterns.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill provides personalized hydration targets and behavioral guidance as if generally applicable, but it does not warn users that hydration needs vary significantly with kidney disease, heart failure, pregnancy, medications, age, and other medical factors. In a health-adjacent tool, omission of a clear non-medical disclaimer and escalation guidance can lead users to follow unsafe advice or delay seeking appropriate care.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The urine color chart offers quasi-diagnostic self-assessment and medical recommendations, including 'seek medical attention' and 'see a doctor,' without clearly explaining that urine color can be misleading and that some symptoms warrant urgent evaluation regardless of self-assessment. This can create false reassurance or unsafe self-triage, especially when users rely on the chart instead of professional care.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill stores health-related and lifestyle data such as body weight, hydration habits, caffeine/alcohol intake, and possibly other personal factors in a local JSON file without an explicit privacy notice. While the storage is local, users are not warned about the sensitivity, retention, or exposure risk of this data on shared systems or backups.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.