Security audit

Mental Reset Suite

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and not malicious, but it needs review because it persists sensitive mental-health and sleep data and uses an unpinned installer without enough user-control safeguards.

Install only if you are comfortable with an agent storing mental-health, sleep, and alcohol-related information across sessions. Before using it, confirm where that state is stored, how to delete it, whether reminders are user-approved, and prefer a pinned or preinstalled trusted ClawHub CLI instead of running an unpinned `npx` command.

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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:15
Finding: Unpinned Package Execution Through npx
Content: View full analysis
Remediation: View remediation
`. - Use a lockfile or equivalent mechanism to pin transitive dependencies. - Retrieve packages only from an explicitly configured, trusted registry. - Verify package provenance and integrity through registry signatures, checksums, or an approved internal mirror. - Disable or review dependency lifecycle scripts where the package manager supports doing so. - Re-audit the package before updating the pinned version. - In managed deployments, install the reviewed CLI ahead of time and invoke the trusted local binary rather than allowing `npx` to resolve the latest remote release dynamically. ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:370
Finding: Persistent Storage of Sensitive Mental-Health and Sleep Data Without Defined Protections
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description uses broad distress terms like 'burned out,' 'exhausted,' 'can't sleep,' and 'needs a complete mental reset,' which are common everyday phrases and may cause the skill to activate in contexts where the user did not explicitly request this protocol. In a mental-health-oriented skill, unintended invocation is more concerning because it can steer sensitive conversations, collect health-related data, or override a more appropriate response path.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 92% confidence
Finding: The install command references npx clawhub without a pinned version, so consumers may fetch whatever package version is current at execution time. This creates a supply-chain risk: a compromised upstream release, typo-squatted dependency path, or unexpected breaking change could alter behavior at install time.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The 'When to Use' section contains multiple ambiguous activation examples such as exhaustion, Sunday-night insomnia, dreading Monday, and starting fresh after a breakdown or health crisis. These are high-collision signals in normal conversation, and in this context they increase the chance the agent launches a structured protocol and begins tracking sensitive mental-health state when another intervention or simple answer would be more appropriate.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.