billing-budget-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a data ingestion surface that processes external content, which could be exploited to deliver hidden instructions to an AI agent.\n
- Ingestion points: The
run.pyscript reads JSON data from a file path provided via the--inputcommand-line argument (line 30).\n - Boundary markers: The skill does not implement delimiters or specific instructions to ignore potential commands embedded within the business signals it processes.\n
- Capability inventory: The script has the capability to read and write files on the local file system (lines 30, 32, 33).\n
- Sanitization: No content validation or sanitization is performed on the input payload before it is processed or used in the output summary.
Audit Metadata