annual-operating-plan
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/aop_reconciliation.py) to process financial data provided in a local JSON configuration file. This is standard functionality for the skill's stated purpose. - [DATA_EXPOSURE]: The script reads a configuration file provided via the
--configargument. It only performs local calculations and prints the results to the standard output. There is no evidence of data being transmitted to external servers. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied financial data from a JSON file. While this represents an ingestion point for untrusted data, the script uses a safe JSON parser (
json.load) and only performs numerical calculations, presenting no significant risk of prompt injection or instruction override.
Audit Metadata