resuming-roadmap-work
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from files within the project repository to determine the next workflow step, which could allow instructions in those files to influence the agent's behavior.
- Ingestion points: SKILL.md reads content from roadmap files (*-roadmap.md), state files (roadmap-state.json), and queue files (batch-plan-queue.md).
- Boundary markers: No specific delimiters or warnings are used to isolate ingested content from agent instructions.
- Capability inventory: The skill interacts with the user via AskUserQuestion and delegates execution to other skills.
- Sanitization: Content from files is used without explicit sanitization or strict schema enforcement.
- [NO_CODE]: The skill contains only markdown instructions and configuration, with no executable scripts or binary files.
Audit Metadata