ClawHub
Back to skill

Security audit

team-memory

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent team-memory purpose, but it should be reviewed because it instructs agents to persist identifiable team and workstyle information to an external API without clear privacy, retention, or consent guidance.

Review this skill before installing in an organization. Use it only with approval to send team/member information to BlueColumn/Supabase, avoid sensitive or evaluative personnel details unless authorized, and confirm retention, deletion, and access controls for stored memories.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly demonstrates sending detailed employee profile and behavioral data to a remote third-party API, including strengths, weaknesses, preferences, and responsiveness patterns, without any privacy warning, consent guidance, or data-minimization controls. This creates real risk of unauthorized processing of personnel data, policy noncompliance, and over-collection of sensitive workplace information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This example performs an authenticated POST to a remote endpoint and includes detailed team-member personal/work-profile content in the request body. Even though the behavior is part of the skill's intended function, it is still a genuine security/privacy concern because it normalizes external transmission of employee-related data to a third-party service without safeguards or disclosure.

Content

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

Store each member's role, strengths, and how they like to work.

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": "TEAM: Priya owns onboarding and UX; strongest at synthesis, weak at saying no. Daniel owns backend; prefers written RFCs over meetings. Dana does data; responds fastest in the afternoon.", "title": "team map - v1"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow and documentation encourage persistence of team context and working agreements but do not disclose that this information is stored externally or may have privacy, governance, or confidentiality implications. In practice, this omission can cause users or downstream agents to store internal norms, staffing signals, and operating practices in a third-party system without informed review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.