Back to skill

Security audit

Fx Base

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed helper skill for sending authenticated requests to a specific feima-lab API, with install and supply-chain cautions but no artifact-backed malicious behavior.

Install this only if you trust feima-lab and the API endpoint, because dependent skills can send user-provided data and an FX_AI_API_KEY-backed request to that service. Prefer a pinned or otherwise verified installation source instead of the short unversioned install command when possible.

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:36
Finding

Unpinned Third-Party Installation Through npx

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 36 and 39
Vulnerability Type: Supply-chain exposure through unpinned installer and dependency resolution
Risk Level: Medium

bash
# ClawHub (recommended)
npx skills install fangshan101-coder/fx-base

# npm
npx skills install fx-base

Technical Analysis

Both installation commands invoke the unversioned skills npm package through npx. If it is not already available locally, npx may download and execute the currently resolved package. The commands also install an unversioned Skill using either a repository-style identifier or a short registry name.

No exact package version, immutable commit hash, checksum, signature, lockfile, or other integrity control is specified. Therefore, the installer or installed Skill can change after this artifact has been reviewed. The short fx-base identifier also depends on registry name resolution without documenting a verified publisher or canonical source.

This finding concerns the documented installation workflow. The audited project itself contains no confirmed malicious payload.

Attack Path

  1. An attacker compromises the account, repository, release process, or registry package associated with the installer or target Skill.
  2. The attacker publishes a modified version containing malicious installation or runtime behavior.
  3. A user follows the documented unpinned npx skills install ... command.
  4. npx resolves and executes the currently available installer package.
  5. The installer resolves and installs the currently available target content without validating it against an audited immutable version or expected digest.
  6. The compromised code executes with the permissions of the user running the installation.

Impact Assessment

Successful exploitation could permit arbitrary code execution under the installing user's account. The resulting access would be limited by that account's ...[truncated 407 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin the skills installer to an exact reviewed version rather than allowing npx to resolve the latest release.
  2. Pin the installed Skill to an immutable release version or commit hash.
  3. Publish cryptographic checksums or signatures and verify them before installation or execution.
  4. Document the canonical package publisher and source repository.
  5. Remove or clarify the ambiguous short-name installation command unless publisher identity and package provenance can be verified.
  6. Use lockfiles and reproducible installation procedures where the tooling supports them.
  7. Review pinned updates before changing the documented versions or integrity metadata.
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Lp1

High
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The module performs outbound network requests via fetch to a remote API endpoint, but this capability is not covered by declared permissions. Undeclared network access is dangerous because a base dependency can silently transmit prompts, user data, or secrets to an external service, reducing transparency and increasing the blast radius across all importing skills.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The module performs outbound network requests via fetch to a remote API endpoint, but this capability is not covered by declared permissions. Undeclared network access is dangerous because a base dependency can silently transmit prompts, user data, or secrets to an external service, reducing transparency and increasing the blast radius across all importing skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description says the skill triggers '当你看到领域 skill 的 CRITICAL 声明要求读取本文件时触发', but it does not define what specific wording counts as a trigger or when the skill should not activate. This is a markdown/manifest-scoped vague trigger because the condition depends on an imprecise natural-language cue rather than a narrow, explicit invocation rule.

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.