Security audit

streaming-audio-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-built for persistent ambient audio memory, but it handles highly sensitive audio with broad scope and little visible user control.

Review this skill carefully before installation. Only use it for devices and environments where you have clear authorization and notice/consent, and confirm how BlueColumn stores, protects, retains, and deletes uploaded audio and derived transcripts before sending real streams.

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)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill explicitly stores persistent, per-device audio memory and enables later recall, but provides no warning or controls around consent, retention, minimization, or handling of highly sensitive content captured from cars, doorbells, wearables, and kiosks. Because ambient audio often contains bystander conversations, credentials, health data, or other regulated information, persistent storage materially increases privacy and compliance risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill’s invocation guidance is very broad: it encourages use for ambient monitoring and answering questions about device audio history without explicit authorization, consent, or scope limits. In an agent ecosystem, this can cause over-triggering in ordinary surveillance or Q&A contexts and lead to inappropriate collection or recall of sensitive audio.
Content: No source excerpt is available for this finding.

External Transmission