hedgefund-goldman-stock-screener
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts (
dip_scanner.py,fundamentals.py,triage.py) using a virtual environment located at/Users/engineer/.venv/bin/python3to perform technical and fundamental stock analysis. - [EXTERNAL_DOWNLOADS]: The skill uses
web_fetchto retrieve external market data, such as sector medians and analyst price targets, from third-party financial websites. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external content and user-provided investment profiles.
- Ingestion points: The skill ingests user input via the investment profile template and external text retrieved through
web_fetchcalls. - Boundary markers: While the skill enforces a structured report format, it lacks explicit delimiters or instructions to ignore embedded commands within the fetched external data.
- Capability inventory: The skill has the ability to execute shell commands (via Python scripts), perform network operations, and write files to the local
.cache/directory. - Sanitization: There is no documented evidence of sanitization or filtering for the data ingested from external web sources before it is processed by the agent.
Audit Metadata