viral-loops
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
membraneCLI for managing referral data and executing actions via shell commands. - [EXTERNAL_DOWNLOADS]: The documentation requires installing the
@membranehq/clipackage via npm to enable the integration tools. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: Untrusted data enters the context from Viral Loops API endpoints via
membrane action runandmembrane request. Boundary markers: No delimiters or warnings are provided to separate external data from instructions. Capability inventory: The skill uses shell commands via themembraneCLI and performs network requests. Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent.
Audit Metadata