blog-image
AI image generation and editing for blog content powered by Gemini via MCP. Generates hero images, inline illustrations, social preview cards, and OG images, and edits existing ones. Supports 6 domain modes (Editorial, Product, Landscape, UI/Web, Infographic, Abstract). Works standalone or internally from blog-write and blog-rewrite; falls back gracefully when MCP is unavailable. Use when user says "blog image", "generate hero image", "blog illustration", "edit blog image", "OG image".
76
96%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The skill explicitly instructs users/agents to rephrase and retry prompts to circumvent image safety filters and persist until successful, which is guidance to evade safety controls without clear malicious intent.
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-provided free text as the user’s explicit command arguments (e.g., `/blog image generate <idea>` or `/blog image edit <path> <instructions>`) and then constructs an internal prompt for `gemini_generate_image`/`gemini_edit_image`, with no step that reads arbitrary outsider-authored external feed content.
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 an MCP server that runs "npx -y @ycse/nanobanana-mcp@1.1.1" (installed/executed at runtime) which fetches and runs remote npm package code linked from https://github.com/YCSE/nanobanana-mcp, so remote code is executed as a required runtime dependency.
- Repository
- AgriciDaniel/claude-blog
- Commit
2500d4c
- 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.