3scribe
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include installing the
@membranehq/clipackage from the NPM registry. This is an expected dependency provided by the vendor to facilitate the integration.- [COMMAND_EXECUTION]: The skill utilizes themembranecommand-line interface to perform operations such as authentication, action discovery, and running transcription jobs.- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it retrieves and processes content from the 3Scribe service. - Ingestion points: Data returned from transcription jobs and job searches via
fetch-transcriptandsearch-transcription-jobs. - Boundary markers: There are no explicit delimiters or instructions provided to separate the retrieved transcription content from the agent's internal instructions.
- Capability inventory: The skill has access to the
membraneCLI which can perform network requests and execute arbitrary actions within the Membrane platform. - Sanitization: The skill does not define any sanitization or filtering logic for the data ingested from the external service.
Audit Metadata