30x-seo-content-writer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted data from external files and user inputs.
- Ingestion points: The skill reads local files including
CONTENT-CALENDAR.md,SEO-STRATEGY.md, andCOMPETITOR-ANALYSIS.mdusing theReadtool. It also accepts direct user input for topics, keywords, and search intent. - Boundary markers: The instructions lack explicit delimiters or instructions to ignore potential commands embedded within the SEO plan files or user-provided keywords.
- Capability inventory: The skill environment is limited to
WebFetch(network read) andRead(file read) as specified in theallowed-toolsconfiguration. It does not have access to tools for file writing or arbitrary command execution. - Sanitization: There are no documented procedures for sanitizing or validating the content extracted from the strategy files before it is used to generate the final blog post.
Audit Metadata