Security audit

potplayer

Security checks for vulnerabilities and agentic risk

Overview

This PotPlayer skill is mostly a media launcher, but it should be reviewed because it also exposes webcam and screen-capture commands without clear consent or scoping.

Install only if you want an agent to launch PotPlayer on your machine. Review or remove the webcam and screen-capture examples, and require explicit confirmation before opening remote streams, camera input, or screen recording.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:101
Finding: Capture-Device Capabilities Exceed the Declared Media-Playback Scope
Content: View full analysis
Remediation: View remediation

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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger description is very broad, covering generic requests to play videos, audio, anime, TV series, or movies. In an agent environment, this can cause the skill to be selected for a wide range of casual requests and then execute local applications or open remote media URLs without sufficiently narrow intent matching, increasing the chance of unintended invocation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill documents opening network streams and later exposes webcam and screen-capture capabilities, but does not include warnings, consent requirements, or safety checks. In an agent-controlled setting, these features could lead to privacy-invasive behavior, unexpected network access, or system-impacting actions if invoked from ambiguous user prompts.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.