Security audit

Viz Table

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but its generated report includes an unsafe formula feature that can execute arbitrary JavaScript in the browser page.

Review before installing. Use this only with non-sensitive data unless the formula evaluator is replaced with a restricted arithmetic parser and the ECharts dependency is pinned or bundled. The automatic /tmp HTML output and browser opening are disclosed and expected, but formula input should not be treated as safe spreadsheet syntax in its current form.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:96
Finding: Arbitrary JavaScript Execution Through Unsafe Formula Evaluation
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:36
Finding: Mutable Third-Party ECharts Script Loaded Without Integrity Verification
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Behavioral ASTexec() Call, eval() Call, Dynamic Import
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 (5)

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill explicitly instructs the generated HTML to take a user-provided formula string and pass it to eval(), which permits arbitrary JavaScript execution in the browser context rather than only arithmetic over dataset columns. Because the file is then opened automatically, any user who interacts with the formula box can trigger script execution with access to the page DOM and any browser-reachable resources allowed in that context.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill not only uses eval() on untrusted formula input, but does so without any warning that arbitrary expressions will be executed inside the generated HTML. This creates a hidden code-execution surface disguised as a calculation feature, making the context especially dangerous because users expect spreadsheet-like arithmetic, not JavaScript execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description and the embedded required prompt text instruct the skill in Chinese and require a Chinese response flow, but there is no opt-in or indication that the skill is intentionally limited to Chinese-speaking users. This conflicts with the language/locale policy criterion for natural-language constraints without user choice.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill writes a file to /tmp and later launches it in a browser without clearly warning or obtaining consent for filesystem modification and program execution. In an agent setting, silent side effects reduce transparency and can surprise users or violate least-astonishment and approval expectations.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The stated purpose is to read local data files and generate an HTML chart, but the instructions explicitly require running a Bash command. Spawning a shell is a broader execution capability than necessary for data transformation and HTML generation, even if the end goal is opening the result in a browser.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.