selection-randomizer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as Google Sheets and local files (CSV, Excel). Ingestion points: Data enters the agent context via Google Sheets URLs and local files like entries.csv or contest-entries.xlsx (SKILL.md). Boundary markers: The instructions do not define specific delimiters or warnings to separate external data from instructions. Capability inventory: The skill uses the agent's ability to read external file contents and present selected data to the user. Sanitization: There are no instructions for validating or filtering the content of the external data sources for potentially malicious prompt content.
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any scripts or executable code blocks.
Audit Metadata