Back to skill

Security audit

coaching-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-built for coaching memory, but it tells agents to automatically store and recall coaching notes in an external service without clear user consent, minimization, or retention guidance.

Install only if you are comfortable with coaching summaries and progress notes being sent to BlueColumn for persistent recall. Avoid storing sensitive personal details unless the user explicitly agrees, and prefer brief redacted summaries until retention and deletion controls are clear.

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
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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs agents to persist coaching notes and progress data to an external BlueColumn service but does not warn that this may include sensitive personal, behavioral, or goal-tracking information. In a coaching context, users may disclose highly sensitive material, so omitting disclosure and consent guidance creates a real privacy and data-handling risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill explicitly sends user coaching content to a remote endpoint using authenticated POST requests. While external transmission is core to the feature, it is still a genuine security/privacy concern because the transmitted content can contain sensitive personal progress notes, and the workflow encourages automatic recall and storage without any stated minimization or consent checks.

Content

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

Store

bash
curl -X POST .../agent-remember \
  -H "Authorization: Bearer <key>" \
  -H "Content-Type: application/json" \
  -d '{"text": "Goal: ship MVP by Sep. Check-in 7/31: on track, risk — design sign-off.", "title": "coaching-memory - note"}'