decision-dashboard

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python script (run.py) via the Bash tool to generate financial reports. This behavior is consistent with its implementation as a code-backed financial tool.\n- [EXTERNAL_DOWNLOADS]: The skill references 'akshare' as a source for financial data, which involves fetching market information from external servers. This is a standard and expected requirement for market monitoring functionality.\n- [PROMPT_INJECTION]: The skill ingests data from local files and directories to build its dashboard, creating an indirect prompt injection surface.\n
  • Ingestion points: Data is read from files and directories provided via the --file and --dir CLI arguments as described in SKILL.md and run.py.\n
  • Boundary markers: No specific delimiters or boundary instructions are present in the skill's templates to isolate ingested symbol data.\n
  • Capability inventory: The skill leverages Bash, Read, and Glob capabilities to access and process system files.\n
  • Sanitization: The instruction files do not specify explicit data sanitization or filtering logic for the content of processed data files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:02 AM