seo-content-marketing-skill-factory
Warn
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation requires the user to clone a complete repository from
https://github.com/JaguarPillage/r04-alirezarezvani-claude-code-skill-factory-seo.gitto access the actual command implementations. This external repository is not from a verified or trusted organization. - [COMMAND_EXECUTION]: The installation guide instructs users to execute multiple shell commands, including
git clone,mkdir, andcp -r, which involves moving unverified external scripts into the agent's sensitive skills directory (~/.claude/skills/). - [PROMPT_INJECTION]: The skill is designed to ingest and process content from any user-provided URL for SEO audits and analysis, which is a vector for indirect prompt injection.
- Ingestion points: External domains and website content processed via
/content-audit,/technical-seo, and/competitor-gapcommands. - Boundary markers: None identified in the provided instruction file to differentiate between tool instructions and ingested web content.
- Capability inventory: The skill has capabilities for network access (crawling), file system operations (exporting CSV/MD reports), and command-line interactions.
- Sanitization: No sanitization or filtering methods are documented for the external data being processed by the agent.
Audit Metadata