kiro-spec-batch
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate orchestration of sub-agents for documentation generation. It reads and writes local project files such as roadmap and specification documents within the expected project directory structure. No external network requests or unauthorized data access patterns were identified.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes user-provided project files.
- Ingestion points: The instructions require reading .kiro/steering/roadmap.md and .kiro/specs/*/brief.md to parameterize sub-agent tasks.
- Boundary markers: Data from these files is interpolated into prompts without delimiters or warnings to ignore potential instructions within the content.
- Capability inventory: The skill spawns sub-agents and writes local Markdown and JSON files. It does not execute shell commands or access the network.
- Sanitization: No validation or filtering is applied to the content of the roadmap or brief files.
Audit Metadata