nika-migration
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze untrusted external data in the form of existing automation scripts, CI jobs, or prompt chains, creating a surface for indirect prompt injection attacks.
- Ingestion points: The 'Port protocol' (Step 1) in SKILL.md directs the agent to 'Read the source completely' and inventory its inputs, outputs, side effects, and credentials.
- Boundary markers: The instructions do not include explicit delimiters or 'ignore embedded instructions' warnings for the source material being analyzed.
- Capability inventory: The skill utilizes CLI tools (nika compile, nika check, nika run, nika test) and describes workflow tasks that involve shell command execution (exec:) and credential handling (secrets:). A malicious script could contain instructions designed to influence the agent's behavior during the analysis or migration phase.
- Sanitization: There are no instructions for the agent to sanitize, filter, or escape the content of the source scripts before processing them.
Audit Metadata