Back to skill

Security audit

social-parser

Security checks for vulnerabilities and agentic risk

Overview

The skill has a clear social-media parsing purpose, but it asks users to install an unpinned global CLI and gives limited disclosure about sending links to a remote service.

Review this carefully before installing. Use it only with Douyin or Xiaohongshu links you are comfortable sending to a remote parser, and avoid private or sensitive URLs. If the CLI is needed, prefer a pinned, reviewed version and avoid running the global npm install with elevated privileges.

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:129
Finding

Unpinned Global Installation of a Third-Party CLI Package

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 129–136
Vulnerability Type: Insecure third-party dependency installation
Risk Level: Medium

Vulnerable Code

markdown
## Supplement: When the Command Is Unavailable

If executing the `gnomic` command reports that the command cannot be found, install `gnomic-cli` with the following command:

```bash
npm install -g gnomic-cli

gnomic-cli open-source repository: https://github.com/huyi9531/gnomic_cli

text

### Technical Analysis

The Skill instructs users or agents to install the latest available version of `gnomic-cli` globally from the npm registry. The dependency is not pinned to a reviewed version, and the instruction does not require package-integrity verification, provenance validation, or review of npm lifecycle scripts.

A link to a GitHub repository does not establish that the package downloaded from npm was built from the referenced source revision. Consequently, the effective package content can change after this Skill has been audited. npm packages may also execute lifecycle scripts during installation, which means a compromised or malicious release could run code immediately.

The global `-g` installation increases the exposure compared with a project-local installation. It places the executable in a globally accessible command location and may modify shared package directories. This finding does not establish that the current package is malicious; the risk arises from trusting an unpinned, externally mutable package without integrity controls.

### Attack Path

1. An attacker compromises the npm publisher account, the package release process, or a future release of `gnomic-cli`.
2. The attacker publishes a modified package version containing a malicious lifecycle script or executable.
3. A user or agent encounters the documented “command not found” condition and follows the Skill instruction.
4. `npm install -g gnomic-cli` resol
...[truncated 1018 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the dependency to a specifically reviewed version, such as gnomic-cli@<audited-version>, rather than installing the latest release.
  2. Prefer a project-local dependency governed by a committed lockfile instead of a global installation.
  3. Verify package provenance and integrity using registry integrity metadata, trusted checksums, signatures, or reproducible-build evidence.
  4. Review the exact npm artifact and its lifecycle scripts rather than relying only on the linked source repository.
  5. Disable lifecycle scripts during installation where compatible, for example by using npm's --ignore-scripts option.
  6. Run the CLI in a sandbox or restricted environment with minimal filesystem access, no unnecessary credentials, and controlled network access.
  7. Document the expected npm package name, publisher identity, approved version, checksum, and secure update process.
  8. Avoid elevated privileges for installation and execution.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description uses broad verbs like '解析'、'获取'、'抓取'、'提取'、'分析这个视频', which can match many ordinary user requests beyond this specific skill's safe scope. Over-broad routing can cause the agent to invoke this skill on loosely related prompts and send user-provided links or content to the external gnomic tool unnecessarily, increasing data exposure and unintended network actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Although the skill notes that requests access a remote API, it does not clearly disclose that user-supplied social-media links and potentially related fetched content are transmitted to an external service/tool for processing. This weak transparency can cause users to unknowingly share sensitive or private URLs with a third party, especially when analyzing private, semi-private, or internal tracking links.

Content

No source excerpt is available for this finding.