The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches external quickstart documentation using WebFetch or context7 to guide the integration process. This introduces a surface where untrusted data from documentation sites could contain instructions designed to manipulate the agent's file-scaffolding or command-execution behavior.\n
Ingestion points: Step 2 pulls content from official documentation URLs using WebFetch or compound-engineering:context7.\n
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the fetched documentation.\n
Capability inventory: The skill is capable of writing multiple files to the local filesystem (Step 3) and executing shell commands for environment configuration and testing (Steps 5 and 6).\n
Sanitization: There are no explicit instructions to sanitize, escape, or filter the content retrieved from external documentation sources.\n- [COMMAND_EXECUTION]: The skill automates the configuration of environment variables and the execution of smoke tests using shell commands.\n
Evidence: Step 5 uses vercel env add and heroku config:set to manage application secrets. Step 6 uses curl and node -e to verify API connectivity and SDK functionality. These actions are aligned with the skill's primary purpose of automating developer setup tasks.

toolify