Security audit

Reel Check

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a proportionate video privacy review using local source checks and visual inspection of rendered frames.

Use this as a review aid, not a guarantee: inspect brief transitions and audio as well as sampled frames. Keep extracted images private and delete them afterward. Review proposed wording and attribution changes before applying them.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (1)

Description-Behavior Mismatch

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared purpose depends on examining what viewers can actually see in the published media. The supplied code explicitly does not inspect footage or MP4 files and instead checks selected source files. Although those checks could support a publication review, they do not implement the core promised capability and may flag source content that never appears on screen while missing leaks burned into frames.
Content: No source excerpt is available for this finding.