alterlab-rma-proposal-writer
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by design, as it must process external data to fulfill its role. Ingestion points: External funding guidelines retrieved via web search and project-specific local files (notes, pilot data). Boundary markers: The instructions do not define explicit delimiters to separate external data from the system logic. Capability inventory: The skill has the ability to read and write files within the project directory and perform web searches. Sanitization: There are no instructions for validating or filtering content retrieved from the web or project files before use.
Audit Metadata