enhance-email-deliverability
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates an attack surface where malicious instructions could be embedded in the external data it is designed to audit.
- Ingestion points: The agent is instructed to observe SPF/DKIM/DMARC records and a real message's Authentication-Results headers as specified in Phase 0 and Phase 1 of SKILL.md.
- Boundary markers: No specific instructions or delimiters are provided to ensure the agent treats these external data inputs as potentially untrusted strings rather than instructions.
- Capability inventory: The skill provides the agent with the ability to apply DNS and configuration changes to infrastructure (SKILL.md Phase 0), creating a path for an indirect injection to influence system state.
- Sanitization: No sanitization logic for the ingested headers or DNS records is defined.
Audit Metadata