coassemble
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the NPM registry, which is a tool provided by the vendor for platform integration. - [COMMAND_EXECUTION]: The integration uses the
membraneCLI to manage connections and execute actions such as listing, creating, and running platform-specific tasks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from the external Coassemble platform. * Ingestion points: Data is retrieved from Coassemble using actions like
list-courses,get-student, andlist-members. * Boundary markers: No specific delimiters or instructions are provided to distinguish external data from the agent's instructions. * Capability inventory: The skill has broad capabilities to modify data in Coassemble, including creating and deleting members, groups, and enrollments. * Sanitization: No data validation or sanitization procedures are mentioned for the content retrieved from the external API.
Audit Metadata