paper7-ask
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill follows standard procedures for information retrieval and synthesis without any signs of malicious intent, unauthorized data access, or network exfiltration.- [NO_CODE]: No executable scripts or binary files are provided within the skill; it relies entirely on instructional text for tool-calling.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads content from external academic sources and local storage without explicit boundary markers or sanitization.
- Ingestion points: Data retrieved via 'paper7 search', 'paper7 get', and 'paper7 kb read' enter the conversation context.
- Boundary markers: The instructions do not define specific delimiters to isolate external content from the agent's core instructions.
- Capability inventory: Includes the ability to write to the knowledge base using 'paper7 kb write'.
- Sanitization: No validation or filtering is specified for the ingested content.
Audit Metadata