sales-enablement
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/check-output.pyused to validate sales deliverables. This script is executed locally to check for the presence of specific keywords and minimum length requirements. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: The
scripts/check-output.pyscript reads the content of generated deliverables (specified by the user or agent) to validate them. - Boundary markers: None identified in the script or instructions to distinguish between instructions and data within the validated file.
- Capability inventory: The skill uses a Python script for file reading and logic checks. The agent is instructed to create various sales documents based on user input.
- Sanitization: There is no explicit sanitization or filtering of the content being read by the validation script, which could potentially allow embedded instructions in the deliverable to influence subsequent agent behavior if the agent processes the script's output or the file content further.
Audit Metadata