The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the npx skills command to interact with a remote registry for searching, listing, and adding capabilities. The allowed-tools configuration correctly limits the scope to this specific command.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of third-party code and configurations from the inference.sh registry (e.g., npx skills add inference-sh/skills@ai-image-generation). These resources are downloaded and integrated into the agent's environment at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external registry when performing search or list operations, creating a potential attack surface.
Ingestion points: The output of npx skills search and npx skills list commands is processed by the agent to display available skills.
Boundary markers: There are no specific delimiters or instructions provided to the agent to treat descriptions from the registry as untrusted data.
Capability inventory: The skill has the ability to execute shell commands (npx skills) and modify the agent's capabilities by adding new skills.
Sanitization: There is no evidence of sanitization or validation of the metadata returned by the remote registry before it is presented to or processed by the agent.

related-skill