The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the snapp-mcp package from the Python Package Index (PyPI) using the uvx tool. This package contains the logic for the skill's tools and involves running code from the skill's author.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that are not under the direct control of the agent or the user.
Ingestion points: Data is retrieved from the Snappfood and SnappMarket platforms through tools such as food_reviews, market_reviews, food_menu, and market_store_products (SKILL.md).
Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions that might be embedded within the retrieved data.
Capability inventory: The skill uses specific tools for querying APIs but does not demonstrate capabilities for file system modification or arbitrary command execution.
Sanitization: There is no evidence that the external content is sanitized or filtered before being presented to the agent's context.
[COMMAND_EXECUTION]: The documentation provides instructions for the user to execute shell commands (e.g., claude mcp add ...) to configure the environment and install the required tools.

snapp