welcome-series
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
WebFetchtool to ingest data from external websites, which presents a risk of indirect prompt injection if the target site contains malicious instructions. - Ingestion points: External brand URLs and subpages (such as
/about,/pricing, or product pages) are fetched and processed in Step 1. - Boundary markers: None are present. The instructions do not specify the use of delimiters or instructions to ignore embedded commands within the fetched content.
- Capability inventory: The skill has access to the
Bash,Read,Write,WebFetch, andWebSearchtools as defined in the YAML frontmatter. - Sanitization: There are no procedures defined to sanitize, escape, or validate the content retrieved from external websites before it is used for content generation.
Audit Metadata