programmatic-seo
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external context files such as
.agents/product-marketing.mdto customize its responses. This ingestion point could theoretically be used to deliver malicious instructions if the file content is attacker-controlled. - Ingestion points: Files
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md(identified inSKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent when processing these external context files.
- Capability inventory: This skill is strictly instructional and does not define any subprocess executions, file-system writes, or network operations.
- Sanitization: There is no explicit sanitization or validation logic defined for the data ingested from the external files.
Audit Metadata