long-term-plan

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes user-supplied objectives and plans to generate automated tasks and documentation.
  • Ingestion points: User responses concerning goals, timelines, and constraints are ingested in Phase 1 and Phase 3 of SKILL.md.
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions embedded within the user's project descriptions.
  • Capability inventory: The skill utilizes create_tasks, update_plan_document, and convert_to_project. The automated task execution (auto) represents a significant risk surface if instructions are injected into task descriptions.
  • Sanitization: Absent; no validation or escaping of external user input is performed before the data is used in tool invocations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 03:07 PM