seo-social-cards

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is focused on SEO metadata hygiene and does not perform any suspicious operations. It includes a section on honesty regarding the limited SEO impact of social tags, which is a positive safety indicator.\n- [PROMPT_INJECTION]: The skill ingests untrusted HTML content from external web pages, creating a surface for indirect prompt injection. This risk is expected and inherent to the skill's primary use case.\n
  • Ingestion points: Metadata and HTML content are extracted from rendered_dom or raw_html (SKILL.md).\n
  • Boundary markers: No delimiters or ignore-instructions are defined for the ingested content in the skill's prompt templates.\n
  • Capability inventory: Employs Bash and WebFetch tools, and suggests automated file modifications via diff generation.\n
  • Sanitization: Data extracted from pages is not explicitly sanitized before being used in reporting or reproduction commands like dom_assert.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 08:09 PM
Security Audit — agent-trust-hub — seo-social-cards