The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external URLs to guide the code scaffolding and configuration process.
Ingestion points: External quickstart URLs fetched via WebFetch and documentation queries performed using context7:query-docs (SKILL.md, Step 2).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between documentation and potentially malicious embedded instructions within the fetched content.
Capability inventory: The skill possesses extensive capabilities including writing multiple source files, modifying environment variables via the Vercel CLI, and executing shell commands for verification (SKILL.md, Steps 3, 5, and 6).
Sanitization: The skill does not describe any sanitization or validation logic for the external documentation before it is used to generate the application's plumbing and client wrappers.
[COMMAND_EXECUTION]: The skill performs several shell-based operations to configure the environment and verify the integration.
Environment Configuration: Uses vercel env add with varying sensitivity flags to manage deployment secrets and public variables.
Smoke Testing: Generates and executes curl and node -e commands to verify the connectivity and functionality of the scaffolded integration (SKILL.md, Step 6).
[EXTERNAL_DOWNLOADS]: The skill retrieves content from the web to ensure integration patterns are up-to-date.
Documentation Fetching: Utilizes WebFetch to download official quickstart guides and SDK documentation from third-party vendor sites.

toolify