ClawHub
Back to skill

Security audit

Sage Week Rhythm

Security checks for vulnerabilities and agentic risk

Overview

This reflection skill is not malware, but it should be reviewed because it reads a personal profile and saves mood/work reflections over time with broad triggers.

Review this before installing if you are not comfortable with a skill reading sage-cognitive profile data, using calendar or memory context, and saving personal work, energy, and values reflections. Prefer explicit invocations like "daily pulse" or "week review," and confirm how to prevent saves or delete prior entries before sharing sensitive information.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly states it reads the user's sage-cognitive profile before every response and logs daily reflections to working memory, but it does not present a clear user-facing notice or consent flow for this data handling. Because the stored content includes energy states, meaningful events, values alignment, and growth observations, users may disclose sensitive behavioral or emotional information without understanding it will be retained and analyzed over time.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger set includes a very generic phrase, "how was today", which overlaps with normal conversation and could invoke the skill unintentionally. In a skill that reads a user profile and writes reflective content into memory, accidental activation can expose contextual data use and create unwanted persistence of sensitive personal reflections.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.