esg-document-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute REST API requests viacurlfor querying ServiceNow records. - [DYNAMIC_EXECUTION]: The skill uses
SN-Execute-Background-Scriptto run server-side JavaScript templates for ESG-specific logic, such as Scope 1, 2, and 3 emissions calculations and dashboard data compilation. These scripts are statically defined as templates within the procedure. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from utility invoices and sustainability reports retrieved from the
sys_attachmenttable. This ingestion presents a potential surface for instructions embedded in these documents to influence the agent. - Ingestion points:
sys_attachment(processing PDF files) andsn_esg_data_pointrecords. - Boundary markers: The instructions do not define specific delimiters to isolate external document content or warn the agent to ignore instructions found within them.
- Capability inventory: The skill has access to
SN-Execute-Background-Script(server-side code execution),Bash, and record modification tools. - Sanitization: The skill does not explicitly describe sanitization or validation of content extracted from attachments before it is used for subsequent logic.
Audit Metadata