account-executive

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides a comprehensive framework for sales discovery, qualification, and pipeline management. Analysis of the scripts and instructions reveals no malicious behavior, obfuscation, or unauthorized access.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts for data analysis. These scripts (scripts/deal_scorer.py, scripts/pipeline_analyzer.py, scripts/win_loss_analyzer.py) are self-contained, use standard libraries, and are limited to processing local files provided via command-line arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from sales CSV/JSON files. However, the risk is mitigated by the narrow scope of the agent's task and the use of structured data processing scripts rather than direct prompt interpolation. 1. Ingestion points: local data files specified in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Local file reading and stdout reporting in Python scripts; no network or subprocess capabilities. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 11:10 PM