seo-audit

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it ingests and processes content from external websites during the audit process.
  • Ingestion points: External website content (crawled by the agent), local brand files (~/.claude-marketing/brands/), and agency SOPs.
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to ignore instructions that might be embedded in the audited website content.
  • Capability inventory: The skill facilitates network-based crawling and local file read operations to manage brand profiles and standard operating procedures.
  • Sanitization: There is no mention of sanitizing or validating external website data before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:23 AM