telnyx-sip-java

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface.\n
  • Ingestion points: External data enters the agent context through API calls like client.connections().list() and client.ips().list() in SKILL.md.\n
  • Boundary markers: There are no markers or instructions provided to the agent to treat API responses as untrusted data or to ignore embedded instructions.\n
  • Capability inventory: The skill has significant capabilities across all scripts, including delete, create, and update methods for infrastructure components (e.g., client.credentialConnections().delete() in SKILL.md).\n
  • Sanitization: The code examples do not implement or mention sanitization or validation of the data retrieved from the remote API before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:31 AM