planning-jira-task

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements a rigid, sequential pipeline for document generation. Orchestration is restricted to reading local configuration files and dispatching tasks to co-located subagents, ensuring a controlled execution flow.
  • [SAFE]: No network connectivity or external data fetching is requested. All operations are confined to the local filesystem, specifically within the docs/ and project source directories, which prevents data exfiltration risks.
  • [PROMPT_INJECTION]: The skill processes external data which presents a surface for indirect prompt injection.
  • Ingestion points: Data is read from docs/<TICKET_KEY>-tasks.md and docs/<TICKET_KEY>-task-<TASK_NUMBER>-decisions.md.
  • Boundary markers: Content is delimited by specific Markdown headers and field labels (e.g., ## Definition of done).
  • Capability inventory: The skill is limited to reading the codebase and writing markdown artifacts to the docs/ directory; it has no access to network or arbitrary shell execution tools.
  • Sanitization: Input is sanitized by extracting only specific, validated fields into the execution brief, preventing the broader task list from influencing downstream planning stages.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 02:47 PM