seo-meta
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests untrusted data from the user or environment and interpolates it into generated HTML/React code, creating an attack surface for code injection.
- Ingestion points:
agents/seo-generator.mdgathers page and business details from user input or by reading project files. - Boundary markers: The skill lacks delimiters or instructions to ignore embedded instructions in the ingested data.
- Capability inventory: The agent uses the
Writetool to output the generated content, and the provided React component renders this data. - Sanitization: The
templates/meta-component.tsxusesJSON.stringify()for script tags, which is vulnerable to XSS if the input data contains</script>tags.
Audit Metadata