plan-agile-development

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to run local project commands such as lint, test, and build, as well as a specific development script scripts/dev-check.sh. These operations are standard for development automation and occur within the project context.
  • [DATA_EXPOSURE]: The skill reads and writes to local project-related files (Markdown and JSON). It does not access sensitive system paths or credentials, and its file operations are limited to project task management.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it ingests data from external project files like tasks/todo.json and current-sprint.json.
  • Ingestion points: PROJECT.md, current-sprint.json, and tasks/todo.json referenced in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: File system writes to project directories and execution of local shell commands.
  • Sanitization: No specific sanitization or validation of the file contents is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:37 PM
Security Audit — agent-trust-hub — plan-agile-development