audit
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it requires the agent to analyze untrusted data from external websites (e.g., page content, robots.txt, and sitemaps).
- Ingestion points: External website source code, robots.txt files, and XML sitemaps retrieved during the audit process.
- Boundary markers: Absent. The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the external data being analyzed.
- Capability inventory: The skill is a set of markdown instructions and does not define any subprocess, shell execution, or sensitive file-writing capabilities.
- Sanitization: No sanitization, escaping, or filtering of the fetched external content is specified.
- [EXTERNAL_DOWNLOADS]: The skill provides links to external tools at seojuice.com. These are provided as optional resources for the user and do not involve automated background downloads or remote code execution.
- [SAFE]: No hardcoded credentials, obfuscation, or persistence mechanisms were detected. The skill consists entirely of markdown-based instructions and checklists.
Audit Metadata