seo-content-writer

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown files and reference templates. There is no executable code or automated scripts included in the package.
  • [NO_CODE]: The skill package contains no Python scripts, JavaScript files, shell scripts, or configuration files that execute commands. All functionality is defined through natural language instructions.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data.
  • Ingestion points: User-provided content briefs, target keywords, and competitor URLs (defined in SKILL.md and references/instructions-detail.md).
  • Boundary markers: The instructions do not specify the use of delimiters for external content to prevent the agent from obeying instructions embedded in the source material.
  • Capability inventory: The skill's actions are limited to writing markdown files to memory/content/ and updating local cache files (memory/hot-cache.md).
  • Sanitization: No specific sanitization or filtering of external content is mentioned before it is incorporated into the draft.
  • [DATA_EXPOSURE]: No hardcoded credentials or sensitive file paths were identified. The use of Search Console is consistent with the stated purpose and relies on platform-managed connections.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:30 PM
Security Audit — agent-trust-hub — seo-content-writer