sedna
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the Membrane CLI package (@membranehq/cli) from the vendor's repository.
- [COMMAND_EXECUTION]: Directs the agent to execute shell commands using the membrane CLI for integration tasks and API requests.
- [PROMPT_INJECTION]: The skill's ability to ingest data from SEDNA and perform actions creates a surface for indirect prompt injection. 1. Ingestion points: Data retrieved from the SEDNA API (SKILL.md). 2. Boundary markers: None specified. 3. Capability inventory: Running actions and API requests via membrane (SKILL.md). 4. Sanitization: No sanitization or filtering of external content is defined.
Audit Metadata