lighthouse
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI tool (
@membranehq/cli) via the NPM registry to facilitate the integration. - [COMMAND_EXECUTION]: The skill uses various
membraneCLI commands to handle authentication, create connections, and execute actions against the Lighthouse API. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as ticket contents, messages, and milestone descriptions from Lighthouse. This represents an attack surface where untrusted data could contain instructions intended to influence the agent's behavior, although no specific exploitation is present in the skill itself.
- Ingestion points: Lighthouse ticket data, messages, and project metadata retrieved via
membrane action runormembrane request. - Boundary markers: None explicitly defined in the instructions for data retrieval.
- Capability inventory: The skill can perform network operations via the Membrane proxy and execute predefined actions.
- Sanitization: Not explicitly defined; relies on the agent platform's default handling of tool outputs.
Audit Metadata