rapid7-insight-platform
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to install the
@membranehq/clipackage via npm. This is a legitimate utility provided by the skill's author (membrane) for platform interaction. - [COMMAND_EXECUTION]: The instructions involve executing various
membraneCLI commands to perform authentication, connection management, and data retrieval. These operations are restricted to the functionality of the Rapid7 Insight Platform integration. - [DATA_EXFILTRATION]: The skill facilitates the movement of security data (vulnerabilities, users, assets) from Rapid7 to the agent's context. This behavior is consistent with the skill's stated purpose of platform management.
- [PROMPT_INJECTION]: As the skill retrieves and processes external security findings and reports, it contains an attack surface for indirect prompt injection.
- Ingestion points: Data is ingested through the
membrane action runandmembrane requestcommands. - Boundary markers: No specific delimiters are used to wrap the retrieved data within the prompt.
- Capability inventory: The agent has the ability to execute shell commands (via the CLI) and perform network requests through the Membrane proxy.
- Sanitization: No explicit sanitization of the external API responses is mentioned, though this is typical for data-integration skills.
Audit Metadata