reporting-and-figure-export
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill recommends verifying tool versions using shell commands such as
python -c "import <module>; print(<module>.__version__)". This is a standard development practice for ensuring environment compatibility. - [PROMPT_INJECTION]: The skill is designed to process external analysis tables and metadata. This represents a surface for indirect prompt injection where malicious instructions could theoretically be embedded in the data processed by the agent.
Audit Metadata