Security audit

Blog Writer Free

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a blog-writing template, but it asks for broad command, file, API, and callback capabilities that are not clearly scoped for that purpose.

Install only if you are comfortable with a blog-writing skill that may be granted file and shell authority. Prefer running it in a constrained environment, do not provide real API keys unless you know which service is being called, and require explicit approval before it reads/writes files, runs commands, or sends callbacks.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Behavioral ASTexec() Call, eval() Call, Dynamic Import
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Intent-Code Divergence

Medium

Confidence: 87% confidence
Finding: The skill documentation is internally inconsistent about whether it performs platform publishing or external API integration. Such contradictions can mislead users and host agents about the actual trust boundary, causing them to authorize networked or publishing behavior they did not intend.

Context-Inappropriate Capability

Medium

Confidence: 96% confidence
Finding: The skill requests exec capability even though its stated purpose is blog writing, SEO, and formatting. Unnecessary command execution materially expands the attack surface because any prompt-influenced workflow could invoke shell commands, access local environment data, or chain into file and network operations.

Vague Triggers

Medium

Confidence: 78% confidence
Finding: The activation text is broad and ambiguous, encouraging invocation for loosely related writing and content tasks without clear boundaries. Overbroad triggers increase the chance the skill is selected in inappropriate contexts, where its read/write/exec capabilities could be exposed to untrusted inputs or used beyond the user's expectations.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill declares read, write, and exec tools but the user-facing description does not clearly foreground these privileged capabilities. This creates a consent and transparency gap: users may invoke what appears to be a harmless writing tool while unknowingly granting file-system and command-execution authority.

Static analysis

No suspicious patterns detected.