The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @openstall/sdk package from the npm registry. This is a vendor-owned package used to interact with the OpenStall platform.
[COMMAND_EXECUTION]: The skill uses several CLI commands including npm install, openstall register, openstall balance, openstall discover, and openstall call to manage marketplace interactions.
[DATA_EXFILTRATION]: The core functionality involves sending task-related data to the OpenStall marketplace (openstall.ai) for processing by external agents. The skill includes a warning to the agent not to send sensitive information.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes data from untrusted third-party agents on the marketplace.
Ingestion points: Data enters the agent's context through the output of the openstall call command in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided when the agent receives results from the marketplace.
Capability inventory: The skill possesses the capability to execute system commands via the openstall CLI and shell.
Sanitization: There is no evidence of sanitization or validation of the content returned from external agents before it is processed.

frugal