skills/sinch/skills/sinch-sdks/Gen Agent Trust Hub

sinch-sdks

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were identified in the skill instructions or referenced scripts.
  • [EXTERNAL_DOWNLOADS]: The skill references standard package installations for Node.js (@sinch/sdk-core), Python (sinch), Java (sinch-sdk-java), and .NET (Sinch) from official registries. These downloads target official vendor-owned libraries.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch external documentation from developers.sinch.com. While this is an ingestion point for external data, it targets an authoritative and trusted source.
  • Ingestion points: Documentation links at developers.sinch.com (referenced in SKILL.md).
  • Boundary markers: SKILL.md includes a 'Source of Truth' section that provides explicit rules for the agent on how to handle and prioritize this external data.
  • Capability inventory: No dangerous tool capabilities such as arbitrary command execution, file system writes, or network exfiltration tools are used in this skill.
  • Sanitization: The skill does not implement specific sanitization or filtering of the external documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:41 PM
Security Audit — agent-trust-hub — sinch-sdks