The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli global package. This is a vendor-owned tool from the same author as the skill and is used to facilitate platform interactions.
[COMMAND_EXECUTION]: The instructions involve executing various membrane CLI commands for authentication, action discovery, and execution. These commands are integral to the skill's primary function of integrating with SnapScan.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data retrieved from external SnapScan API endpoints.
Ingestion points: Data from the SnapScan service enters the agent context via membrane action run and membrane request outputs in SKILL.md.
Boundary markers: The instructions do not define boundary markers or include warnings to ignore instructions embedded in the external data.
Capability inventory: The skill executes subprocess commands using the membrane CLI across multiple integration steps.
Sanitization: No sanitization or validation of the ingested external data is performed before it is presented to the agent.

snapscan