email-sequence
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional content and templates for email marketing. No malicious patterns, such as prompt injection, obfuscation, or unauthorized data exfiltration, were detected across the analyzed files.
- [PROMPT_INJECTION]: The skill allows for context-aware responses by reading a local configuration file (
.claude/product-marketing-context.md). While this pattern introduces a potential surface for indirect prompt injection if the ingested file contains malicious content, the implementation is consistent with standard agent configuration and does not currently pose a direct threat. - Ingestion points:
.claude/product-marketing-context.md(SKILL.md) - Boundary markers: None provided within the instruction set.
- Capability inventory: The skill is primarily instructional; it references external integrations but does not invoke system-level tools directly.
- Sanitization: Not specified.
Audit Metadata