Back to skill

Security audit

Web Video Presentation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local helper for creating screen-recordable web presentations, with no evidence of hidden access, exfiltration, or unsafe persistence.

Install only if you want an agent to scaffold local browser-based presentation projects. Review the generated package before running npm install because it uses latest React/Vite dependencies, and choose the target directory deliberately so new files are created where you expect.

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
  • 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 (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
- Create a minimal Vite + React + TypeScript presentation skeleton using [create-video-presentation.mjs](scripts/create-video-presentation.mjs):

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 10)May include surrounding context.

md
- ID: `fec-web-video-presentation`
- Category: `design-ui`
- Version: `2.9.0`
- Source: `skills/fec-web-video-presentation/SKILL.md`

## Description

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README says to use the skill when turning an article, talk script, lesson, product demo, or narrated explanation into a presentation, which spans many common content-creation tasks. It also mixes broad English and Chinese trigger phrases without negative examples or exclusion conditions, making it unclear when this skill should activate versus more general design, presentation, or video skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description says to use the skill for turning an article, lesson, product demo, or narrated explanation into a presentation, and lists triggers like "web video" and "dynamic demonstration." These phrases are broad and lack explicit boundaries or negative examples, which could cause the skill to match ordinary presentation-related requests beyond the intended specialized workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says to use the skill for turning an article, talk script, lesson, product demo, or narrated explanation into a presentation, and also lists trigger phrases like 'web video' and 'dynamic demonstration'. Several of these phrases are broad and lack negative examples or scope boundaries, which could cause the skill to match general requests more often than intended.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description is broadly phrased ('use when turning an article, talk script, lesson, product demo, or narrated explanation...') and includes many overlapping triggers, which can cause an agent to invoke the skill in situations beyond its intended scope. In agent ecosystems, vague invocation boundaries increase the chance of inappropriate activation, prompt-routing errors, or accidental exposure of user content to a skill that was not the best or safest match.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest explicitly calls out 'Chinese triggers include ...' but does not clarify whether language handling is optional, user-selected, or part of a region-specific configuration. This can create a locale-policy concern because language behavior is being prescribed in natural language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.