plan-to-tasks
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted project plans and specifications to generate task descriptions in a JSONL format. This represents an indirect prompt injection surface where instructions hidden within a plan could be propagated into the agent's work queue.
- Ingestion points: User-supplied project plans, requirements documents, and technical specifications (specified in
SKILL.mdandrules/information-extraction.md). - Boundary markers: Absent. The instructions do not require the use of delimiters or 'ignore' instructions for the content extracted into the task descriptions.
- Capability inventory: The skill is authorized to create structured JSONL files (
plan/issues.jsonl) and integrates with implementation skills like/tdd-integrationwhich may execute the generated tasks. - Sanitization: Absent. There is no requirement for filtering, escaping, or validating the external content before it is interpolated into the JSON structure.
Audit Metadata