seo-content-marketing-claude-skills
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation instructions direct users to clone a repository from 'github.com/bansheegiraffecode/r17-behisecc-awesome-claude-skills-seo.git'. This is an unverified third-party repository that does not match the stated author's identity or official vendor resources.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites through commands like '/content-audit' and '/technical-seo'. Mandatory Evidence Chain: 1. Ingestion points: External URLs passed as arguments to audit commands (SKILL.md). 2. Boundary markers: Absent; the skill does not specify delimiters or warnings for the agent to ignore instructions within audited content. 3. Capability inventory: The skill has capabilities for network access (crawling), file writing ('--file' flags), and interaction with local CLI tools. 4. Sanitization: Absent; the skill documentation does not describe any filtering or escaping of the ingested web content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill suite defines commands that involve significant shell interaction, including cloning repositories, managing local directories, and executing system-level SEO tools such as Screaming Frog.
Audit Metadata