handover
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and summarizes multiple external project artifacts to create a handover packet, which establishes a potential vector for indirect prompt injection.
- Ingestion points: The skill is instructed to read from
state/.../phases/phase-NN.md,notes.md,plan.toml, anddesign.mdto gather context (SKILL.md). - Boundary markers: The instructions do not provide specific boundary markers or "ignore embedded instructions" warnings for the agent to use when processing these files.
- Capability inventory: The skill uses
doctrineCLI commands and has the capability to write to.doctrine/*/handover.mdfiles (SKILL.md). - Sanitization: There are no instructions to sanitize or validate the content harvested from the project artifacts before incorporating it into the new agent's context.
Audit Metadata