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