stackshare
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
membraneCLI to perform various tasks including authentication (membrane login), connection management (membrane connect), and running specific actions (membrane action run). - [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the NPM registry, which is the official tool provided by the vendor for managing integrations. - [PROMPT_INJECTION]: A surface for indirect prompt injection exists because the skill processes content from the StackShare API.
- Ingestion points: Data enters the agent's context through the
membrane action runandmembrane requestcommands (SKILL.md). - Boundary markers: No delimiters or 'ignore' instructions are specified for handling data returned from the API.
- Capability inventory: The skill can execute shell commands via the
membraneCLI tool (SKILL.md). - Sanitization: There is no mention of sanitizing or validating the output from StackShare before it is processed by the agent.
Audit Metadata