seo-content-marketing-skill-suite
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions create an indirect prompt injection surface by requiring the agent to ingest and analyze untrusted content from external websites while utilizing high-privilege capabilities such as network access and API authentication.
- Ingestion points: Commands such as
/technical-seo,/content-audit, and/page-speed-seoingest and process data from external URLs. - Boundary markers: Absent. There are no instructions for the agent to use delimiters or safety guidelines to ignore instructions found within the processed web data.
- Capability inventory: The skill manages multiple sensitive API keys (OpenAI, Ahrefs, Semrush) and provides examples for network operations to Slack webhooks and email notifications.
- Sanitization: There is no instruction to sanitize or validate the content fetched from external URLs before processing.
- [COMMAND_EXECUTION]: Integration examples in the documentation demonstrate unsafe shell command execution practices that could be vulnerable if implemented directly by users.
- Evidence: The provided JavaScript integration snippet for Google Sheets export uses
execSyncwith direct string interpolation of thetopicvariable into a shell command, representing a potential command injection vector.
Audit Metadata