adoption-report
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from several external and user-controlled sources, which presents a surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests data from
.ds-ops-config.yml, npm download statistics, Figma REST API responses (including library analytics), GitHub code search results, and documentation platform search logs. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat this external data as untrusted or to ignore any embedded instructions within the pulled content.
- Capability inventory: The skill possesses the capability to perform network operations through integrated tools (GitHub CLI and Figma API) and has the ability to read from and write to the local filesystem for report generation and recurring workflow management.
- Sanitization: The instructions do not define any filtering or sanitization processes for the gathered data, particularly for search logs which are directly influenced by end-user input.
Audit Metadata