define-seo-strategy

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources and local files without explicit sanitization, creating a potential vector for indirect instructions to influence the agent's behavior.
  • Ingestion points: The skill reads CUSTOMER.md, BRAND_GUIDELINES.md, and processes user-provided inputs including website URLs and product descriptions.
  • Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when passing data to the seo-researcher sub-agents.
  • Capability inventory: The skill has the capability to write files to the local directory (SEO_STRATEGY.md) and the system temporary directory (/tmp/seo-research-*.md), and invokes sub-agents for research tasks.
  • Sanitization: There is no evidence of escaping, validation, or filtering of the content retrieved from the website URL or the local markdown files before they are used to generate the final strategy document.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 08:11 AM