cursor-port-github-app-to-origin
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by reading and analyzing local application source code to extract functional requirements, which represents an attack surface for indirect prompt injection if the code contains malicious instructions.
- Ingestion points: Local source code files, manifests, and dependency configurations are read by the agent.
- Boundary markers: While explicit delimiters are not provided for the code blocks, the skill uses a task-specific extraction methodology to scope the agent's focus.
- Capability inventory: File system read access for analysis, file system write access for report generation, and network GET access for fetching API documentation.
- Sanitization: The instructions mandate that the agent must exclude all internal metadata, such as file paths, repository names, and module names, from the feedback generated for the vendor.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation and OpenAPI specifications from
https://cursor.com/docs/api/origin/*. This is a well-known service associated with the skill's stated purpose and is used solely to provide technical context for the porting task.
Audit Metadata