The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via npm. This is a vendor-owned resource used to facilitate communication between the agent and the BugHerd API.
[COMMAND_EXECUTION]: Relies on the membrane CLI tool to perform authentication, discover available actions, and execute API calls. This is the intended design of the skill for interacting with the Membrane platform.
[DATA_EXFILTRATION]: Provides a proxy request feature (membrane request) that transmits data to the BugHerd API. This mechanism is authenticated and managed by the vendor's infrastructure to avoid local credential exposure.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data from external BugHerd records.
Ingestion points: BugHerd resource data (tasks, comments, etc.) enters the agent's context through CLI output.
Boundary markers: Not present; the instructions do not define delimiters for segregating external content.
Capability inventory: The agent can perform write operations like create-task and arbitrary API calls through the membrane request utility.
Sanitization: Not present; the skill does not implement specific filtering for data returned from the API.

bugherd