proof
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute
curlcommands for all API and bridge interactions. - [EXTERNAL_DOWNLOADS]: Fetches document state and configuration from
www.proofeditor.aiand the local host bridge atlocalhost:9847. - [DATA_EXFILTRATION]: Transmits document markdown and metadata to the external service
proofeditor.ai, which is essential for its primary document-sharing functionality. - [PROMPT_INJECTION]: Reads and processes untrusted markdown content from external documents, creating a potential surface for indirect prompt injection.
- Ingestion points: Document content retrieved from API endpoints.
- Boundary markers: Not defined in the instructions.
- Capability inventory: Tools like
Bash,Write, andWebFetchare available to the agent. - Sanitization: No content validation or sanitization of external document data is specified.
Audit Metadata