forecasting-time-series-data
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process time-series data from CSV files. While data ingestion is a known surface for indirect prompt injection (where instructions could be embedded in data rows), the skill uses standard mathematical libraries for analysis and contains no malicious example payloads.
- [NO_CODE]: The documentation in
scripts/README.mdmentionsforecast.py,evaluate.py, andpreprocess.py, but these script files are missing from the provided skill package. This does not indicate a security flaw but limits the verification of the full forecasting logic.
Audit Metadata