hr-business-partner

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious intent, obfuscation, or unauthorized data access patterns were identified in the skill metadata or templates.
  • [COMMAND_EXECUTION]: The skill documentation includes examples of executing local Python scripts (e.g., scripts/workforce_plan.py, scripts/comp_analyzer.py) to analyze HR metrics and planning data.
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection: 1. Ingestion points: Untrusted data from external CSV files such as survey_results.csv, headcount.csv, and terminations.csv are processed by the agent (SKILL.md). 2. Boundary markers: Absent; there are no delimiters or instructions to differentiate between data and potentially embedded malicious instructions in the CSV files. 3. Capability inventory: The skill is documented to execute shell commands and Python scripts locally (SKILL.md). 4. Sanitization: Absent; no validation, escaping, or filtering of the input file content is mentioned in the provided documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 05:52 PM