product-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data files (e.g.,
events.csv,funnel.csv) using a Python script, which the agent then interprets to provide recommendations. This creates a vulnerability where malicious instructions within the data could influence the agent's output.\n - Ingestion points: External CSV files processed by the
scripts/metrics_calculator.pyutility as shown in the examples.\n - Boundary markers: The workflow does not include instructions for using delimiters or other isolation techniques to separate data from potential instructions.\n
- Capability inventory: The skill executes a local Python script to perform analytics, with the agent interpreting the resulting data to formulate product strategy.\n
- Sanitization: There is no evidence of input validation or output sanitization to mitigate the risk of processing malicious content embedded in the datasets.
Audit Metadata