fda-qsr-audit-prep
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
scripts/qsr_readiness_score.pyandscripts/dhf_completeness_checker.py) to automate readiness scoring and Design History File (DHF) validation. These scripts are invoked via the command line and operate on user-provided configuration files. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data from YAML configuration files.
- Ingestion points: Data is ingested through the
--configand--dhfarguments in the provided Python scripts. - Boundary markers: There are no explicit instructions or delimiters used to separate user-provided data from agent instructions during processing.
- Capability inventory: The skill's capabilities are limited to reading local files and generating reports (stdout or file write); no network operations or arbitrary command execution was detected.
- Sanitization: The scripts implement a custom, restrictive YAML parser that converts input values into basic scalar types (strings, integers, floats, booleans), preventing the execution of code or complex objects often associated with standard YAML loaders.
Audit Metadata