blog-image
AI image generation and editing for blog content powered by Gemini via MCP. Claude acts as Creative Director - interpreting intent, selecting domain expertise, constructing optimized 6-component prompts (Subject + Action + Context + Composition + Lighting + Style), and orchestrating Gemini for blog-quality results. Generates hero images, inline illustrations, social preview cards, and OG images. Edits existing blog images. Supports 6 blog-optimized domain modes (Editorial, Product, Landscape, UI/Web, Infographic, Abstract). Works standalone via /blog image or internally from blog-write and blog-rewrite workflows. Falls back gracefully when MCP is not configured. Use when user says "blog image", "generate hero image", "blog illustration", "social card", "generate blog image", "edit blog image", "image generate", "blog cover image", "inline image", "OG image".
79
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
2 findings: 2 critical severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Three URLs are official Google documentation (low risk), but the GitHub repo (https://github.com/YCSE/nanobanana-mcp) is an external, project-pinned package source (supply‑chain risk / unvetted third‑party) and should be treated as suspicious until vetted.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The code does not contain an explicit in-repo backdoor, but it configures and relies on a pinned third‑party MCP npm package (@ycse/nanobanana-mcp@1.1.1) that will be executed via npx with the user's GOOGLE_AI_API_KEY (either written to config or injected via env), creating a high-risk supply‑chain / credential‑exfiltration vector if that package is malicious or compromised.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime workflow only ingests outsider-authored free text provided as the user command argument (e.g., `/blog image generate <idea>` / `/blog image edit ... <instructions>`) and then uses it to construct a crafted prompt and call the MCP image tools.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill configures and runs the external MCP package via npx (PINNED_PACKAGE="@ycse/nanobanana-mcp@1.1.1"), which causes remote code to be fetched and executed at runtime from the package/repo (https://github.com/YCSE/nanobanana-mcp) and is required for image generation, so this is an execution-time external dependency.
- Repository
- AgriciDaniel/claude-blog
- Commit
aec971a
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.