pharma-intelligence-brief
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's workflow requires the execution of a provided Python script (
scripts/generate_report.py) to transform gathered data into a structured HTML report. This process is used to ensure output consistency and safety. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a data aggregator for information from external sources such as patent databases, scientific literature, and clinical trial registries. While this creates an attack surface for indirect prompt injection, the skill implements robust sanitization by applying HTML escaping to all external content within the
generate_report.pyscript before the final report is rendered.
Audit Metadata