workspace-planning

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of pyyaml via pip. This is a well-known and standard library for parsing YAML data.
  • [COMMAND_EXECUTION]: The skill executes a local script scripts/planning.py to perform deterministic operations like reviewing progress, updating statuses, and linking project changes. The script uses yaml.safe_load() to prevent YAML-based injection attacks.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No network operations or unauthorized data access were identified. The script only interacts with project-specific YAML files in the planning/schedules/ directory.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes external YAML data, it employs a state machine to validate all status transitions and uses safe parsing methods, effectively mitigating risks associated with untrusted data ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 12:50 AM