programmatic-seo
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external context files (such as .agents/product-marketing.md) and user-provided inputs to generate SEO strategies. This creates a potential vector for indirect prompt injection if the ingested data contains hidden instructions.
- Ingestion points: The agent is instructed to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding.
- Boundary markers: There are no explicit instructions to the agent to treat the content of these files as data only or to ignore any instructions embedded within them.
- Capability inventory: The skill is primarily focused on strategy generation and documentation; it does not appear to use dangerous capabilities like arbitrary command execution or network writes based on the ingested data.
- Sanitization: The instructions do not specify any validation or sanitization steps for the data read from external files.
- [EXTERNAL_DOWNLOADS]: The skill provides links to external documentation and integration guides hosted on GitHub.
- Evidence: References to github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/ploy.md and related registry links.
- Context: These links point to a well-known service (GitHub) and are provided for informational purposes regarding tool integrations and partner disclosures.
Audit Metadata