data-updater
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's codebase was audited for malicious patterns, obfuscation, and unauthorized access; no security violations or high-severity threats were found.\n- [COMMAND_EXECUTION]: The skill orchestrates the execution of local Python scripts (
update_fund_data.pyandclassify_funds.py) to perform its core functions. These commands are restricted to the skill's own internal logic and do not utilize untrusted inputs for command construction, posing no significant risk.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from external CSV files, which presents a surface for indirect prompt injection.\n - Ingestion points:
scripts/update_fund_data.pyreads user-provided CSV files via thecsvmodule.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are present in the parsing logic.\n
- Capability inventory: The skill is limited to reading CSVs and writing JSON files (
fund_data.json, etc.) using standard Python file operations.\n - Sanitization: The parsing logic includes robust type conversion (e.g.,
int(),float(),re.matchfor risk levels), which serves as a basic defensive layer, although no specific natural language sanitization is applied to fund names or descriptive fields.
Audit Metadata