The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the official @membranehq/cli package from the npm registry, which is the expected tool for interacting with the author's platform.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to log in, connect to Oxylabs, and execute scraping actions. These operations are within the stated scope of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data scraped from external websites via Oxylabs actions.
Ingestion points: Scraped website data returned by the membrane action run command.
Boundary markers: The instructions do not specify any markers or delimiters for the ingested content.
Capability inventory: The skill has the capability to create new actions, run existing actions, and access the network via the CLI.
Sanitization: No explicit sanitization or filtering of the scraped content is provided within the skill instructions.

oxylabs