skills/reason-machines/marketing-skills/seo-content-marketing-claude-code-skill-suite/Gen Agent Trust Hub
seo-content-marketing-claude-code-skill-suite
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions require cloning a repository from a third-party source (
https://github.com/PrefectFlourish22/r18-anthropics-claude-code-seo.git) that is not affiliated with the stated author or included in the trusted vendors list. This represents a supply-chain risk as the external code is not verified.\n- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for crawling and auditing external websites (e.g.,/content-audit,/technical-seo). Processing untrusted data from these websites creates a surface for indirect prompt injection where malicious instructions on a website could attempt to override the agent's behavior.\n - Ingestion points: External website URLs and their crawled content (HTML, metadata, text).\n
- Boundary markers: The documentation does not specify the use of delimiters or warnings to ignore instructions embedded in crawled data.\n
- Capability inventory: Shell command execution, network requests to third-party APIs, and file system write operations for exporting results.\n
- Sanitization: No mention of sanitization or safety filtering for external content before it is processed by the agent.\n- [DATA_EXFILTRATION]: The skill is designed to interact with multiple external SEO APIs (SerpApi, Ahrefs, Semrush, etc.) and encourages the use of environment variables to store sensitive API keys. Malicious code in the external repository could potentially exfiltrate these keys or sensitive project data to unauthorized domains.
Audit Metadata