battlechain-tutorial
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automatically scans local project files (
src/**/*.solandscript/**/*.sol) using theGlobtool to extract deployment logic and external dependencies. This ingestion of untrusted data into the agent's context creates a surface for indirect prompt injection if the files contain malicious instructions. \n - Ingestion points:
Globtool calls for Solidity files inSKILL.mdduring the pre-scan phase. \n - Boundary markers: Absent; the skill reads file content directly to inform its logic and question flow. \n
- Capability inventory: Uses
AskUserQuestionfor user interaction and generates/modifies local deployment scripts. \n - Sanitization: No explicit sanitization or validation of the content read from local files is mentioned before it is used to influence the agent's behavior.
Audit Metadata