seo-site-audit
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Potential for Indirect Prompt Injection. The skill is designed to ingest and process data from external websites via the
seo crawlcommand and Search Console reports viaseo_run_report. This content is untrusted and could contain instructions designed to manipulate the agent's output or behavior. - Ingestion points:
SKILL.mddescribes tools that fetch external web content and report data. - Boundary markers: None identified. There are no instructions to use delimiters or ignore instructions found within the audited data.
- Capability inventory: Shell command execution via the
seotool and MCP tool invocations. - Sanitization: No explicit sanitization or validation of the ingested external content is described.
- [COMMAND_EXECUTION]: The skill relies on shell command execution (
seo report,seo crawl) to function. While these are legitimate SEO tools, the inclusion of user-controlled parameters like URLs and project names in shell commands represents a surface for potential command injection if the underlying agent does not properly sanitize inputs.
Audit Metadata