define-seo-strategy

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has a surface area for indirect prompt injection through its data ingestion and processing workflow.
  • Ingestion points: The skill reads content from local files including CUSTOMER.md, BRAND_GUIDELINES.md, and SEO_STRATEGY.md. It also ingests product descriptions from user input and the results returned by three seo-researcher sub-agents.
  • Boundary markers: The skill does not employ explicit delimiters (e.g., XML tags or Markdown code blocks with clear labels) or specific instructions to ignore embedded commands when these inputs are interpolated into prompts for the LLM or sub-agents.
  • Capability inventory: The skill possesses the capability to write to the filesystem (creating SEO_STRATEGY.md and log files in /tmp/) and invoke other agents for research tasks.
  • Sanitization: There is no specified logic for sanitizing or validating the content of the ingested files or user-provided descriptions before they are used to generate the final strategy document.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:33 AM