Security audit

Video Promo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward video-promo planning helper that reads project context and writes a plan file, with no evidence of hidden execution or data misuse.

Before installing, be aware that invoking the skill may create or overwrite docs/video-promo.md. Review that file change before committing, especially if your repository already has a video-promo plan.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill instructs the agent to write a generated plan directly to docs/video-promo.md without explicit user confirmation or a prominent disclosure that a repository file will be modified. This can cause unintended file changes, noisy commits, or overwriting of user content, especially when the user only asked for analysis or ideation rather than a filesystem change.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.