ln-222-story-replanner

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted story data and uses it to perform write operations.
  • Ingestion points: Data enters the agent's context through epicData, idealPlan, and existingStoryIds as defined in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or mandatory "ignore embedded instructions" warnings for the external content being processed.
  • Capability inventory: The skill is authorized to perform state-changing operations including save_issue, kanban updates, and provider-specific issue modifications as detailed in the Workflow section of SKILL.md.
  • Sanitization: There is no evidence of content sanitization, escaping, or validation of the external story data before it is interpolated into tool calls or outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 01:53 AM