ClawHub
Back to skill

Security audit

remember-projects

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned but sends and stores potentially sensitive project details in an external BlueColumn/Supabase service with broad automatic-use instructions and little privacy guidance.

Review this before installing if your projects include confidential roadmap, customer, personnel, security, or business data. Use it only with an approved BlueColumn account, get user or organization consent before sending project details, and redact sensitive owner, blocker, milestone, and risk information unless external storage is explicitly allowed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says to use the skill whenever 'an agent manages ongoing work and needs a live picture of every project,' which is a broad natural-language condition that could overlap with many ordinary project-management conversations. It does not define specific trigger phrases, boundaries, or exclusion cases to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The examples encourage sending project details, owner names, milestones, and blockers to a remote third-party API without any privacy notice, consent prompt, or data-classification guidance. This can lead to unintended disclosure of internal operational data and personal information when an agent follows the example verbatim.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

This command performs external transmission of potentially sensitive project metadata to a remote endpoint, including owner identity, milestone timing, goals, and blockers. In the context of an agent skill, the danger is increased because users may treat the example as a routine memory action without realizing it exports business-sensitive information off-platform.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

Store a project the moment it exists, with the outcome, owner, and next milestone.

bash
curl -X POST https://xkjkwqbfvkswwdmbtndo.supabase.co/functions/v1/agent-remember \
  -H "Authorization: Bearer $BLUECOLUMN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "PROJECT: Redesign onboarding flow. Owner: Priya. Goal: cut activation time from 8 to 3 minutes. Next milestone: prototype review Aug 12. Blockers: waiting on design sign-off.", "title": "project - onboarding redesign"}'

Static analysis

No suspicious patterns detected.