hsgt-holdings-monitor

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform command-line operations to activate a virtual environment and execute specialized data runner scripts found in relative paths. Evidence is found in references/data-queries.md.
  • [EXTERNAL_DOWNLOADS]: The skill requires the agent to install Python dependencies from a local requirements file, which triggers package downloads from public registries. Evidence is found in references/data-queries.md.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes external JSON data for analysis while having the capability to execute system commands. Ingestion points: Data returned by the views_runner.py tool as described in references/data-queries.md. Boundary markers: None identified in the prompt templates. Capability inventory: Ability to execute shell commands and Python scripts. Sanitization: No specific data validation or sanitization logic is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:23 AM