referrals
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read local context files such as
.agents/product-marketing.md. This represents a potential surface for indirect prompt injection if these files are populated with untrusted data. - Ingestion points:
.agents/product-marketing.md,.claude/product-marketing.md,product-marketing-context.md(as specified in SKILL.md). - Boundary markers: No explicit instructions are provided to the agent to delimit or ignore potential instructions within these context files.
- Capability inventory: The skill is primarily focused on generating strategic advice and recommendations; it does not contain executable code, file writing operations, or network tools.
- Sanitization: No sanitization or validation of the ingested file content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill provides links to external documentation and a tool registry hosted on GitHub (
github.com/coreyhaines31/marketingskills). These references are informational and link to markdown files for user or agent reference.
Audit Metadata