program-manager

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates program coordination by executing local Python scripts (milestone_tracker.py, portfolio_dashboard.py, and resource_allocator.py) to analyze data and generate reports. These scripts use standard Python libraries and process data from local file paths provided via command-line arguments.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill ingests and processes data from external sources.
  • Ingestion points: The skill loads data from files such as milestones.json, portfolio.json, and resources.json (as shown in script usage) as well as projects.yaml and benefits_plan.yaml (as referenced in SKILL.md).
  • Boundary markers: Absent; the skill does not use delimiters or provide instructions to the agent to disregard nested commands or instructions within the data.
  • Capability inventory: The skill manages high-level program governance and executes shell commands to run its internal analysis scripts.
  • Sanitization: Absent; the Python scripts parse JSON and YAML data and print formatted output without sanitizing the content against potential prompt injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:08 AM