career-market-optimization-engine

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts (calculate_priority.py and calculate_v2c.py) to perform mathematical modeling for salary benchmarking and skill gap prioritization. These scripts are part of the repository and execute safe arithmetic operations on parameters calculated by the agent.
  • [EXTERNAL_DOWNLOADS]: Several workflows, including /job-hunt and /company-research, use the agent's built-in web search capabilities to gather live market data and job postings. This is a core functionality for the skill's purpose and does not involve downloading executable content from untrusted sources.
  • [PROMPT_INJECTION]: The skill processes external Job Descriptions and user-provided resumes, creating an ingestion point for indirect prompt injection. 1. Ingestion points: Job Descriptions (retrieved via search or user input) and user resumes processed in tailoring and audit workflows. 2. Boundary markers: None explicitly defined in the provided workflows for separating untrusted data. 3. Capability inventory: File system write access (saving CVs and Dossier files), web search, and local script execution. 4. Sanitization: No explicit sanitization or validation of the input text before processing is specified in the workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 01:19 PM