technical-scan

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection exists due to the processing of untrusted external data.
  • Ingestion points: The skill ingests stock symbols as arguments and processes external market data artifacts and local datasets via the Read, Glob, and Grep tools.
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings to prevent the agent from obeying instructions that might be embedded within the market data.
  • Capability inventory: The skill has access to Bash (executing python3), Read, Glob, and Grep, allowing it to perform file operations and code execution based on processed data.
  • Sanitization: No explicit sanitization, validation, or escaping logic is present for the symbol input or the data retrieved from external artifacts.
  • [COMMAND_EXECUTION]: The skill is configured to use the Bash tool to execute Python scripts (python3). While this is a standard capability for data analysis skills, it grants the agent the ability to execute arbitrary code on the local system to process technical indicators.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:01 AM