fiorano-software
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/cliNode.js package, which is a trusted tool provided by the platform vendor for managing integrations. - [COMMAND_EXECUTION]: Uses the
membranecommand-line tool to perform actions like connection management and executing integration logic with Fiorano Software. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests data from external Fiorano Software instances.
- Ingestion points: Data retrieved from external endpoints via the
membrane action runandmembrane requestcommands. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the retrieved data.
- Capability inventory: The skill allows the agent to execute shell commands and interact with the filesystem/network via the
membraneCLI as documented in SKILL.md. - Sanitization: There is no explicit logic described for sanitizing or validating the data returned from the external API calls.
Audit Metadata