Back to skill

Security audit

technical-analyst

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for stock technical analysis, but it asks users to install from mutable remote sources and produces actionable trade recommendations without clear financial-risk framing.

Review the exact source before installing, prefer a pinned commit or verified release instead of the README command as written, and treat generated trade setups as informational technical analysis only rather than financial advice. Only provide a Finskills API key you are comfortable using for this service.

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
README.md:21
Finding

Unpinned Third-Party Installer and Mutable Remote Skill Source

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 21–25
Vulnerability Type: Supply-chain exposure through unpinned dependencies
Risk Level: Medium

Vulnerable Code

markdown
## Install

```bash
npx skills add https://github.com/finskills/technical-analyst --skill technical-analyst
text

### Technical Analysis

The documented installation process invokes the npm package `skills` through `npx` without specifying a package version or integrity hash. It also installs the skill from a mutable GitHub repository reference rather than a reviewed commit SHA or signed release.

Consequently, the code and skill instructions installed by this command can differ from the content that was audited. A compromise of the npm package, its publisher account, the GitHub repository, or the repository's default branch could replace the expected installation behavior or skill content with attacker-controlled material.

This is an insecure dependency and supply-chain practice. The reviewed files contain no evidence that the current package or repository is malicious; the risk arises because the installation command does not cryptographically bind installation to the reviewed versions.

### Attack Path

1. An attacker compromises the npm package publisher, the GitHub repository, or an associated maintainer account.
2. The attacker publishes a malicious version of the unpinned `skills` package or modifies the repository's mutable default branch.
3. A user runs the documented `npx skills add` command.
4. `npx` retrieves the currently resolved installer, and the installer retrieves the current repository content rather than the audited revision.
5. Attacker-controlled installation logic or skill instructions are processed with the privileges available to the invoking user or agent.
6. Depending on the malicious replacement and the host's tool permissions, it could alter installed skill files, execute commands through t
...[truncated 783 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin the npm installer to a specifically reviewed version, for example by using npx skills@<reviewed-version>.
  2. Pin the GitHub source to an immutable commit SHA or a signed release rather than the repository's mutable default branch.
  3. Verify downloaded artifacts using a published cryptographic checksum or signature before installation.
  4. Record the reviewed installer version, repository commit, expected hashes, and verification procedure in the installation documentation.
  5. Run installation with the least-privileged account required and avoid exposing unrelated secrets in the installation environment.
  6. Prefer a package manager lockfile or another reproducible installation mechanism where supported.
  7. Periodically review pinned dependencies and update them only after security validation.
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 (3)

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The README instructs users to install the skill via npx skills add from a remote GitHub repository without pinning a specific commit, tag, or immutable package version. That means future changes to the referenced repository or the fetched toolchain could alter what users install, creating a supply-chain risk where malicious or compromised updates are silently pulled at install time.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill provides concrete trading actions including entry zones, stop-losses, targets, and recommended actions, but does not include an explicit warning that this is not financial advice or that following it can materially affect the user's finances. In a finance-oriented skill, this increases the risk that users treat generated output as actionable personalized guidance and incur losses based on model-generated recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The output template is predominantly English, but line L260 uses the Chinese label "Bollinger位置". This introduces a language/locale inconsistency in the user-facing output without offering a language choice or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.