gds-sprint-status
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a Python script located at
{project-root}/_bmad/scripts/resolve_customization.py. This script is part of the vendor's internal project infrastructure and is used to merge configuration layers (base, team, user). - [DATA_EXFILTRATION]: The skill reads project-specific data from
sprint-status.yamlandproject-context.md. This is required for its primary function of summarizing sprint progress and identifying risks. - [PROMPT_INJECTION]: An indirect prompt injection surface exists (Category 8).
- Ingestion points: Reads untrusted project data from
{sprint_status_file}and{project_context}inSKILL.md(Steps 1 and 2). - Boundary markers: None identified. Data is loaded directly into the agent's context.
- Capability inventory: The agent can execute shell commands via Python subprocesses (Activation Step 1, Step 5) and perform file write operations (Step 2).
- Sanitization: No explicit sanitization or escaping of the ingested YAML or Markdown content is performed before interpolation into outputs or instructions.
Audit Metadata