market-screen
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from external files and directories that could contain malicious instructions.
- Ingestion points: The symbols, --file, and --dir parameters in run.py and SKILL.md.
- Boundary markers: Absent; no explicit delimiters or warnings to ignore embedded instructions are provided when processing external content.
- Capability inventory: The skill is authorized to use Bash (to run python), Read, and Glob tools as defined in SKILL.md.
- Sanitization: While ticker formats are validated, the content of CSV files from the --dir path is not sanitized for embedded language model instructions.
- [EXTERNAL_DOWNLOADS]: The skill references the akshare library to fetch market data, which is a well-known and standard financial data utility.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute its core logic via the market-screen/run.py entry point.
Audit Metadata