The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from npm. This is a vendor-owned resource used to interface with the Membrane platform.
[COMMAND_EXECUTION]: The skill utilizes several shell commands via the membrane CLI (e.g., login, connect, action run) to manage integrations and execute scraping tasks. These commands are the intended method of operation for the skill.
[DATA_EXFILTRATION]: No unauthorized data exfiltration was detected. The skill explicitly directs the agent to avoid asking for user API keys, instead using server-side connection management to handle secrets securely.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from web scraping results.
Ingestion points: Data enters the agent context via the output of membrane action run as described in SKILL.md.
Boundary markers: None are specified in the instructions to delimit untrusted web content.
Capability inventory: The skill has the capability to execute shell commands via the membrane CLI, as documented in SKILL.md.
Sanitization: No explicit sanitization or validation steps are provided for the content retrieved from external websites.

zenscrape