market-analyze

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md describe executing a Python script via Bash with interpolated user arguments (<symbol> and --csv PATH). This pattern can lead to command injection if the underlying tool execution logic does not strictly validate or escape shell-sensitive characters in the arguments.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of untrusted market data, particularly when using the --csv PATH argument to load external files.
  • Ingestion points: Arguments passed to run.py (<symbol>) and the contents of the file specified by the --csv PATH parameter.
  • Boundary markers: Absent. There are no delimiters or explicit instructions in the prompt to ensure the agent ignores or sanitizes instructions embedded within the loaded data.
  • Capability inventory: The skill has the capability to execute commands using Bash(python3 *) and read files using Read and Glob tools.
  • Sanitization: No explicit validation or sanitization of the input symbol or the CSV content is performed within the visible code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:01 AM