Technical Blog Writing

• Outcome: Review
• Latest audit: Sep 10, 2026 · 3:50 PM UTC
• Version: 0.1.5

Overview

The skill is mostly a technical-writing guide, but it asks users to run mutable remote installers and includes ungated public posting guidance, so it needs Review before installation.

Install only if you are comfortable using inference.sh and reviewing its installer. Prefer manual download with pinned versions and checksum or signature verification, avoid running curl-to-shell blindly, do not connect or use X posting unless you intend to publish the exact text, and treat each related skill install as a separate unpinned third-party install that should be reviewed independently.

A.I.G

Vulnerability Patterns

• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (2)

T03 · Remote Payload Retrieval and Execution

Error

• Location: SKILL.md:14

Finding

Remote Installation Script Executed Directly Through a Shell

Content

View full analysis

Remediation

View remediation

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:290

Finding

Unpinned Third-Party Tool and Skill Installation

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (8)

External Script Fetching

High

• Category: Supply Chain
• Confidence: 98% confidence

Finding

curl ... | sh executes a remotely fetched script directly in the shell, creating a classic supply-chain and remote code execution risk if the server, transport, or distribution pipeline is compromised. Even with checksum claims elsewhere in the text, the one-line install pattern encourages execution before independent verification and is especially dangerous in a skill document that may be copied verbatim by users.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

Quick Start

bash

curl -fsSL https://cli.inference.sh | sh && infsh login

# Research topic depth
infsh app run exa/search --input '{

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The manifest-style description includes many generic trigger phrases such as "technical writing," "developer content," and "technical content," which can overlap with ordinary requests and unrelated documentation tasks. It does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill is presented as a technical blog writing aid, but it includes an example for posting directly to X, which crosses from content drafting into external publication. That capability is materially more sensitive because it can cause unintended public disclosure, reputational damage, or unauthorized posting if invoked without explicit user confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The markdown includes an outbound X posting example without any warning that it publishes externally or that explicit approval is required. In an agent setting, silent or poorly signposted publication actions are dangerous because they can lead to accidental data release or user-harmful actions beyond drafting.

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.

Context-Inappropriate Capability

Low

• Category: Not specified by scanner
• Confidence: 75% confidence

Finding

The manifest frames the skill as technical blog post writing and writing conventions, not research or web search. While light research may support writing, explicitly invoking an external search app introduces a capability outside the declared writing-centric scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.