medium-seo-publisher
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external keyword research tools and existing Medium articles, which presents a surface for indirect prompt injection. Malicious instructions could be embedded in the content being researched or updated.
- Ingestion points: The skill reads data from external keyword tools, search engine results, and existing Medium story drafts (SKILL.md, references/research.md, references/publishing.md).
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within external data.
- Capability inventory: The skill utilizes agent capabilities for local file writing, external tool calls for keyword research, and authenticated browser interaction for Medium publishing (SKILL.md, references/publishing.md).
- Sanitization: There are no instructions for sanitizing or validating external input before it is processed by the agent.
Audit Metadata