seo-audit

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEDATA_EXFILTRATION
Full Analysis
  • [DATA_EXPOSURE]: The skill accesses sensitive business data stored in the local filesystem to provide brand-aware auditing. Specifically, it reads from ~/.claude-marketing/brands/ for brand profiles, compliance rules, and standard operating procedures (SOPs). While this is within the scope of a marketing automation tool, it represents access to local user data.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves crawling and analyzing content from external URLs provided by users. This creates an attack surface where a malicious website could include hidden instructions designed to influence the agent's behavior, override audit criteria, or manipulate the final report findings.
  • Ingestion points: Technical, on-page, and content audits involve reading HTML and metadata from external web domains.
  • Boundary markers: None specified in the instructions to separate external data from system instructions.
  • Capability inventory: The skill reads local brand files and generates structured reports based on external data.
  • Sanitization: No explicit sanitization or filtering of the ingested website content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 11:41 PM