blockbuster-therapy-predictor
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of a local Python script
scripts/main.pywhich uses standard libraries to perform ranking and scoring of therapeutic technologies based on internal mock data. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it accepts technology filters from the user through command-line arguments. 1. Ingestion points: The
--techargument inscripts/main.py. 2. Boundary markers: The script validates technological inputs against a hardcoded internal list, which acts as a restricted boundary for the input data. 3. Capability inventory: The script can write report files to the local file system. 4. Sanitization: Input strings are stripped and checked against a whitelist of supported technology names before processing. - [SAFE]: The skill uses standard Python libraries and does not perform any external network requests or access sensitive system credentials. All external references target the author's official repository.
Audit Metadata