email-sequence
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is configured to read from an external file (
.claude/product-marketing-context.md) to inform its email generation. This creates a surface where instructions embedded in that context file could influence the agent. - Ingestion points:
.claude/product-marketing-context.md(referenced in SKILL.md). - Boundary markers: Absent. The instructions do not explicitly tell the agent to ignore instructions found within the context file.
- Capability inventory: The skill primarily generates text copy. No subprocess calls, network operations, or file-write capabilities were found in the provided files.
- Sanitization: Absent. The skill treats content from the context file as trusted information.
- [Safe Behavior] (SAFE): The skill's primary function is to act as an expert assistant for marketing. All provided reference files (
references/copy-guidelines.md,references/sequence-templates.md) contain standard educational material and templates without any executable code or malicious payloads.
Audit Metadata