Security audit

Grief Navigation Basics

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent grief-support guidance, but it asks the agent to persist very sensitive grief and mental-health details without clear consent, retention, deletion, or storage safeguards.

Review this skill carefully before installing. Its advice is broadly aligned with grief support, but users should know it may retain intimate information about a loss, check-ins, self-harm, depression, and substance use across sessions. Prefer installing only if the platform offers clear controls to review and delete saved state, and avoid running the unpinned install command in privileged environments.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:316
Finding: Persistent Storage of Sensitive Bereavement and Mental-Health Data Without Defined Safeguards
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:15
Finding: Unpinned Package Execution in Installation Command
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill persistently stores highly sensitive data including grief details, mental-health indicators, self-harm flags, substance-use signals, and check-in history, but it does not present a clear user-facing notice or consent flow for retention. In this context, the sensitivity is especially high because the data concerns crisis status and intimate life events; unauthorized access, over-retention, or unexpected reuse could cause significant privacy and safety harm.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 89% confidence
Finding: The install command invokes npx clawhub without pinning an explicit package version, which means the skill may fetch and execute whatever version is current at install time. That creates a supply-chain risk: a malicious or compromised upstream release could run code in the installer context, and the mental-health context does not reduce that technical exposure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.