The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the user to install the @membranehq/cli package from the NPM registry, which is a legitimate download of the vendor's own tool from a well-known service.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to manage authentication, discover API actions, and execute requests against the Wuf platform. These commands are necessary for the skill's primary functionality and use the vendor's official toolset.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes data retrieved from external Wuf API endpoints.
Ingestion points: External data enters the agent's context through membrane action run and membrane request commands as described in SKILL.md.
Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions when handling API responses from Wuf.
Capability inventory: The agent has the capability to perform network requests and execute actions via the membrane CLI tool.
Sanitization: There is no documentation of sanitization or validation of the data received from the external API before processing.

wuf