r20-glebis-seo-content-marketing-skills
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill suite is designed to ingest and process large amounts of untrusted data from external websites through commands like
/content-audit,/technical-seo, and/competitor-gap. This behavior introduces a surface for indirect prompt injection, where a malicious third-party website could host hidden instructions designed to manipulate the agent's output or behavior during the analysis process. - Ingestion points: External web content retrieved during site crawls, competitor analysis, and URL-based audits (specified in
SKILL.md). - Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill performs network operations to fetch external content and generates AI-driven reports and content briefs based on that data.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external URLs.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to load or clone its full implementation from an external GitHub repository (
OhmWhaleIncrease/r20-glebis-claude-skills-seo). As this repository is not associated with the vendor or a known trusted organization, loading its code or configuration poses a supply chain risk where the remote content could be modified without oversight.
Audit Metadata