promo-discount-impact-review-ecommerce

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local utility script at ../scripts/promo_impact.py to perform data analysis on provided files. This is a standard method for modularizing complex logic within a skill directory structure.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as daily revenue CSVs and discount code exports, which creates a potential surface for indirect prompt injection.
  • Ingestion points: User-provided data files including daily orders, discount code usage exports, and COGS basis files.
  • Boundary markers: Not explicitly defined in the skill instructions to separate input data from the agent's processing context.
  • Capability inventory: Executes local Python scripts for calculations and generates analytical reports for the user.
  • Sanitization: No specific sanitization or validation routines are described for the incoming data streams.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:24 AM