openfort
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the official Openfort CLI package (
@openfort/cli) via NPM and the subsequent installation of an MCP server. These are standard vendor-provided tools used for the intended purpose of platform interaction. - [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and processing content from external repositories, creating an attack surface where malicious instructions could be embedded in the documentation or source code.
- Ingestion points: Documentation pages and SDK source code are retrieved from GitHub repositories (e.g.,
openfort-xyz/openfort-js) using MCP tools. - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions found within the processed data.
- Capability inventory: The skill allows the agent to search documentation, read source files, and execute various Openfort CLI commands (e.g., creating accounts, managing policies).
- Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from external sources before it is processed by the agent.
Audit Metadata