skills/reason-machines/marketing-skills/magicstarfishboost-seo-content-marketing-skill-suite/Gen Agent Trust Hub
magicstarfishboost-seo-content-marketing-skill-suite
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites via URL parameters in commands like
/content-auditand/technical-seo, which could potentially contain malicious instructions designed to influence the agent. • Ingestion points: Website content retrieved from<url>parameters defined inSKILL.md. • Boundary markers: No specific boundary markers or instructions to ignore embedded content are defined in the provided documentation. • Capability inventory: The skill is designed to perform network requests for site crawling and API interactions, and it writes to local log files. • Sanitization: The documentation does not outline specific sanitization or filtering steps for data retrieved from external URLs. - [NO_CODE]: This skill contains only markdown instructions and configuration examples in
SKILL.mdand does not include any executable code, scripts, or binaries.
Audit Metadata