The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation from external URLs (mcp.swiggy.com). This creates a vulnerability surface where instructions embedded in the external documentation could potentially influence the agent's behavior.
Ingestion points: In SKILL.md, the agent is directed to fetch data from multiple endpoints, including https://mcp.swiggy.com/builders/llms.txt, llms-full.txt, and various markdown files under the /builders/docs/reference/ path.
Boundary markers: The skill does not define specific delimiters or instructions to treat the fetched content as data only, nor does it provide warnings to ignore embedded commands within the fetched documentation.
Capability inventory: The skill utilizes WebFetch, curl, and a specific swiggy CLI for network operations and data retrieval.
Sanitization: There are no mechanisms described for sanitizing, validating, or filtering the content retrieved from the external sources before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill fetches documentation and tool schemas from mcp.swiggy.com. This is the intended primary purpose of the skill and utilizes well-known service infrastructure.
[COMMAND_EXECUTION]: The skill references the use of curl and a swiggy CLI tool to perform network requests for documentation retrieval.

swiggy-mcp-docs