data-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to query and analyze data from external sources, which creates a surface for indirect prompt injection.
- Ingestion points: The skill processes user questions and retrieved data from external databases such as BigQuery (SKILL.md).
- Boundary markers: The instructions lack specific guidance for the agent to ignore or delimit potentially malicious instructions embedded within retrieved data records.
- Capability inventory: The skill execution environment is scoped with access to
Bash(npm/node),Read,Grep, andGlobtools. - Sanitization: There are no described protocols for sanitizing or validating the content of the data fetched from the external database before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and statistical tools from well-known services.
- Evidence: Provides references to Google Cloud's BigQuery documentation and statistical analysis tools from Evan Miller.
Audit Metadata