creating-charts
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use common shell utilities such as
bq,psql,jq,awk, andsortto aggregate and format data before visualization. This aligns with the skill's primary function of data processing. - [EXTERNAL_DOWNLOADS]: The skill references a chart specification hosted on a trusted organization's GitHub repository and uses the vendor's own domain (
ampcode.com) for fetching data attachments. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from attachments or inline values to generate interactive charts.
- Ingestion points: Data enters via the
data.valuesfield or external URLs indata.url. - Boundary markers: The content is scoped within
flintcode blocks. - Capability inventory: The skill assumes access to data processing tools like
jq,awk,bq, andpsqlto aggregate data. - Sanitization: No explicit sanitization of data values is required by the instructions, relying on the platform's rendering sandbox.
Audit Metadata