Back to skill

Security audit

Kling 3.0 — Pro Pack on RunComfy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed RunComfy integration for generating Kling 3.0 videos, with normal credential and network use for that purpose.

Install only if you are comfortable using the RunComfy CLI with a RunComfy account token. For better hygiene, prefer a pinned or locally installed CLI version, use a token scoped to this service, avoid exposing unrelated secrets in the same shell, and choose output directories deliberately.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:78
Finding

Unpinned Global Installation of a Security-Sensitive Third-Party CLI

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:78
Vulnerability Type: Unpinned third-party dependency installed globally
Risk Level: Medium

Vulnerable Code Snippet:

markdown
1. **RunComfy CLI**: `npm i -g @runcomfy/cli`

Technical Analysis

The Skill instructs users to install the latest available version of @runcomfy/cli globally without specifying an exact version or verifying package integrity or provenance. Consequently, the code installed and executed can change after this Skill has been reviewed.

This dependency is security-sensitive because the documented workflow gives the CLI access to the RunComfy bearer token, user prompts, image references, generated files, and output directories. The project contains no lockfile, checksum, vendored implementation, or other mechanism for independently verifying the installed CLI version. Its documented network restrictions and token-handling behavior therefore cannot be validated from this repository.

Global installation also increases exposure by placing the package in the user's shared tool environment. npm package installation may execute package lifecycle scripts with the privileges of the user running npm, while subsequent CLI execution operates with that user's filesystem and environment access.

Attack Path

  1. An attacker compromises the npm package, its publisher account, or a future package release.
  2. The malicious release becomes the version resolved by the unpinned npm i -g @runcomfy/cli command.
  3. A user follows the Skill's prerequisite instructions and globally installs the package.
  4. Malicious lifecycle or runtime code executes with the installing user's privileges.
  5. The compromised CLI may read accessible environment variables or configuration files, including RUNCOMFY_TOKEN or ~/.config/runcomfy/token.json.
  6. During normal Skill use, it may intercept prompts, image URLs, generated content, or modify network reque ...[truncated 949 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the CLI to a reviewed exact version, for example:
    bash
    npm install --global @runcomfy/cli@<reviewed-exact-version>
    
  2. Document the expected npm publisher, package provenance, and integrity hash.
  3. Prefer a project-local installation with a committed lockfile instead of modifying the user's global npm environment.
  4. Verify npm registry provenance or signatures before installation and monitor the dependency for publisher or ownership changes.
  5. Disable npm lifecycle scripts during installation where compatible with the package's documented installation process.
  6. Run the CLI under a dedicated, least-privileged account or isolated container with access only to required output directories.
  7. Provide the RunComfy token only for the duration of the command and avoid exposing unrelated secrets in the same environment.
  8. Independently review and document the pinned CLI's actual outbound endpoints, token storage, download validation, and file-size controls rather than relying solely on behavioral claims in SKILL.md.
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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill triggers not only on specific phrases like "kling 3.0" but also on "any explicit ask to generate or animate with Kling 3.0." That catch-all condition is ambiguous because it does not define boundaries or exclusions, making it unclear when the skill should or should not activate.

Content

No source excerpt is available for this finding.