aeon

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it is designed to load and process data from external sources and local files.
  • Ingestion points: Data loading functions such as load_classification and load_from_ts_file documented in references/datasets_benchmarking.md fetch content from remote URLs or local paths.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content within data files were identified.
  • Capability inventory: The skill is granted access to the Bash, Read, Write, and Edit tools, allowing for potential system interaction if data is maliciously crafted.
  • Sanitization: No explicit sanitization or validation of data content is described in the reference documentation.
  • [EXTERNAL_DOWNLOADS]: The skill downloads datasets from external academic and research repositories.
  • Evidence: Documentation in references/datasets_benchmarking.md describes loading data from Zenodo, timeseriesclassification.com, and forecastingdata.org. These are established sources for time series research data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:34 PM