The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using subprocess.run in scripts/prepare_tistory_package.py and scripts/tistory_playwright_cli.py to invoke tools like ImageMagick and the Playwright CLI.- [EXTERNAL_DOWNLOADS]: The skill uses npx in scripts/tistory_playwright_cli.py to download the @playwright/cli package from the official NPM registry, which is a well-known service.- [DYNAMIC_EXECUTION]: Temporary Javascript files are generated in scripts/tistory_playwright_cli.py to be executed within the browser's context for editor automation. The code uses json.dumps for safe serialization of data embedded into these scripts.- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect injection as it processes untrusted user markdown files. Evidence: 1. Ingestion points: User articles are read from disk in scripts/prepare_tistory_package.py via the --source argument. 2. Boundary markers: No explicit markers are used to delimit user content within the generated Javascript templates. 3. Capability inventory: The skill can execute shell commands (via subprocess) and automate browser actions (via Playwright). 4. Sanitization: User content is converted from Markdown to HTML using a library and is escaped using json.dumps before insertion into automation scripts.

tistory-seo-blog-poster