The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a source code repository from GitHub (https://github.com/kkdai/devto-blog-translation-tool). This source originates from the skill's author.\n- [COMMAND_EXECUTION]: The skill instructions involve executing Go commands such as go mod download to fetch dependencies and go run cmd/translator/main.go to run the translation logic.\n- [REMOTE_CODE_EXECUTION]: The process of cloning a remote repository and executing its contents via go run constitutes remote code execution. This behavior is documented as part of the tool's core functionality.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted external data in the form of Dev.to draft articles. Maliciously crafted content within these drafts could potentially influence the agent's behavior during translation or publication.\n
Ingestion points: Draft articles retrieved from the Dev.to API.\n
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the articles.\n
Capability inventory: The skill environment executes Go binaries and makes network requests to external APIs (Dev.to and Google Gemini).\n
Sanitization: No explicit sanitization or filtering of the article content is described before processing.

devto-translator