brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of informational markdown and YAML metadata. There are no scripts, binaries, or shell commands included in the file.
- [INDIRECT_PROMPT_INJECTION]: The skill contains a pattern for reading external context from
.claude/product-marketing-context.md. While this represents an ingestion point for untrusted data, the skill's lack of dangerous capabilities (such as network or shell access) makes this surface safe. - Ingestion points: Reads
.claude/product-marketing-context.mdto establish product marketing context. - Boundary markers: Not present; the skill assumes the context file is valid and trusted.
- Capability inventory: limited to text-based artifacts (reports, tables, mini-docs).
- Sanitization: No validation or sanitization is performed on the ingested context file content.
Audit Metadata