sendblue
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing the '@membranehq/cli' package via NPM, which is a standard procedure for this vendor's integration ecosystem.
- [COMMAND_EXECUTION]: The skill uses the 'membrane' CLI to perform SMS actions and manage service connections.
- [METADATA_POISONING]: The skill description mentions CRM features like 'Leads' and 'Pipelines' which do not match the SMS functionality of Sendblue, likely due to a documentation template error.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses, presenting a surface for instructions embedded in external content. Ingestion points: API responses from 'membrane action run' and 'membrane request' (SKILL.md). Boundary markers: Not specified. Capability inventory: SMS message and campaign management via 'membrane' CLI (SKILL.md). Sanitization: Not explicitly implemented.
Audit Metadata