telnyx-porting-out-java
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define processes for ingesting untrusted data from external API endpoints (e.g., port-out request details, comments, and reports) and provide capabilities to write back to the API (e.g., updating statuses or creating comments), creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested through API responses described in SKILL.md, specifically from methods listing port-outs, events, and comments.
- Boundary markers: None identified in the skill instructions to separate external data from agent instructions.
- Capability inventory: The skill uses the Telnyx Java SDK to perform network operations, including listing (
list()), retrieving (retrieve()), and updating (updateStatus(),create()) port-out information. - Sanitization: No explicit sanitization or validation of the ingested external content is mentioned in the provided examples.
Audit Metadata