commercial-forecaster
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data that could theoretically influence agent behavior if interpreted as instructions.
- Ingestion points: All three core scripts (bookings_forecaster.py, cohort_arr_projector.py, and funnel_confidence_scorer.py) read input from a JSON file provided via the --input command-line argument.
- Boundary markers: The generated Markdown reports do not use specific delimiters or protective instructions to wrap the user-provided data fields, which could lead to an agent misinterpreting data values as instructions.
- Capability inventory: The skill is restricted to mathematical and statistical analysis. It does not perform network operations, execute shell commands, or write to the file system.
- Sanitization: Data from the input file is printed directly into Markdown tables. There is no evidence of escaping or validation logic to prevent malicious strings from altering the structure of the output or injecting prompts.
Audit Metadata