sprint-planning

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to create milestones, labels, and project boards based on sprint planning data. Evidence includes the use of gh api, gh label create, and gh project create within the instructions.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external files. 1. Ingestion points: Reads README/CLAUDE.md, product/**/backlog.md, and product/**/story-map.md. 2. Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the processed data. 3. Capability inventory: Includes file system writes, git commits, and GitHub API interactions. 4. Sanitization: Absent; the skill directly uses values from backlog files to construct GitHub issues and CLI command parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:09 PM
Security Audit — agent-trust-hub — sprint-planning