battlechain
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch and install the
battlechain-liblibrary from thecyfrinGitHub repository using theforge installcommand. - [COMMAND_EXECUTION]: The documentation provides multiple shell commands for blockchain interaction and project management, including contract deployment via
forge script, transaction execution viacast send, and automated workflows usingjust. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by directing the agent to ingest external content to guide its technical behavior.
- Ingestion points: The agent is instructed to fetch the single source of truth for technical reference material from
https://docs.battlechain.com/llms-full.txt(SKILL.md). - Boundary markers: There are no specified delimiters or warnings to ignore instructions that might be embedded in the fetched documentation.
- Capability inventory: The skill enables the use of powerful CLI tools (
forge,cast,just) and local file system modifications (foundry.toml remappings). - Sanitization: No process for sanitizing, validating, or filtering the retrieved documentation is defined.
Audit Metadata