sinch-fax-api
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes inbound fax webhooks and callbacks, which constitutes an indirect prompt injection surface.
- Ingestion points: External data enters the agent context through webhook handlers and callback fields such as filenames, metadata, and error messages, as described in SKILL.md.
- Boundary markers: The skill explicitly instructs the agent to treat inbound content as untrusted data and to ignore any instructions embedded within that data.
- Capability inventory: The skill has the capability to make network requests to the Sinch Fax API and manage fax services.
- Sanitization: The instructions mandate that all inbound content must be validated and sanitized before being used, and never interpolated directly into prompts or code.
Audit Metadata