skills/reason-machines/marketing-skills/r13-danielrosehill-claude-slash-commands-seo/Gen Agent Trust Hub
r13-danielrosehill-claude-slash-commands-seo
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation provides installation instructions that require the user to clone a repository from an unverified GitHub account (Dimensionparail), which contains the functional logic for the commands and workflows.
- Evidence:
git clone https://github.com/Dimensionparail/r13-danielrosehill-claude-slash-commands-seo.gitin SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves auditing and analyzing content from external URLs, which serves as an ingestion point for untrusted data that could contain malicious instructions.
- Ingestion points: Commands such as
/content-audit,/technical-seo, and/competitor-gapingest HTML and data from arbitrary web domains (SKILL.md). - Boundary markers: There is no indication of delimiters or specific safety instructions to distinguish between the content being analyzed and the agent's operating instructions.
- Capability inventory: The skill has the capability to perform network requests to SEO service APIs and write report data to the local file system (e.g., audit.json, prospects.csv).
- Sanitization: The documentation does not describe any sanitization or validation processes for data retrieved from external sources before it is processed by the model.
Audit Metadata