Back to skill

Security audit

explainer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Ofox video-generation workflow with clear cost approval steps, though users should be cautious with the optional unpinned npx install commands for its core dependency.

Before installing or using it, confirm you are comfortable sending source text and prompts to Ofox under your API key and paying for generated clips. If ofox-video-core is missing, prefer a trusted, pinned installer path where possible, and do not let an agent run unpinned npx install commands automatically.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (11)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · CHANGELOG.md (reported line 98)May include surrounding context.

md
Measured: 22.49s of actual speaking plus 5.64s of internal silence in **7
  pauses — exactly the script's 7 sentence boundaries**, ~0.7s each. Speaking
  rate 3.56 w/s. The formula predicts 27.4s for that script; the delivered
  span was 28.13s, with 1.39s of tail and no truncation. **90 words in 8
  sentences needs 30.2s of span and does not fit a 30-second clip.**
- ⚠️ **Count sentences, not only words.** Two 80-word scripts can differ by
  several seconds, and short punchy sentences are the *slower* ones. When a

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Forcing the spoken language to follow the source language without explicit user opt-in can lead to output in an unintended language, causing user harm such as publishing incorrect-language content, bypassing user expectations, or mishandling multilingual inputs. In a media-generation skill, this matters because the resulting video may be billed and produced before the mismatch is discovered.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The skill instructs users to run npx ofox-skills without pinning a specific package version. Because npx resolves and executes the latest published package by default, a compromised upstream release or dependency-chain hijack could cause arbitrary code execution on the host at install time.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown explicitly says the spoken language is 'never-ask' and 'follows the source', and later reiterates that the user's own language should be used automatically. This is a natural-language locale policy constraint without user opt-in, which can deny a user's preferred output language unless they know to request translation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The unpinned npx skills command executes code fetched at runtime from the registry, which exposes users to supply-chain risk if the package or one of its dependencies is tampered with. In a skill file, this is especially sensitive because the instruction explicitly encourages installation outside the current working directory.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

This second unpinned npx ofox-skills reference repeats the same supply-chain exposure: the executed package is not fixed to a reviewed version. If an attacker publishes or compromises a newer release, users following the skill may run malicious code with their local user privileges.

Content

No source excerpt is available for this finding.