welcome-series
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data by using
WebFetchto crawl user-provided brand URLs, as well as secondary pages like/aboutor/pricing(SKILL.md, Step 1). - Boundary markers: Absent. The instructions do not specify any delimiters or safety prompts to prevent the AI from obeying malicious instructions that might be embedded in the HTML or text of the target websites.
- Capability inventory: The skill manifest allows the use of
WebFetch,WebSearch,Bash,Read, andWritetools (SKILL.md, frontmatter). - Sanitization: Absent. The fetched content is processed directly to extract brand voice and product details without a validation or filtering layer.
Audit Metadata