rea-firmware-iot-extension
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (firmware images, EVM bytecode, and signal recordings), which presents a vulnerability surface for indirect prompt injection where malicious instructions could be embedded in analyzed data.
- Ingestion points: Data enters the agent's context through tools such as
extract_firmware,open_binary,inspect_evm_interface, anddecode_signal_recordingas described in the execution pipeline. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" warnings to prevent the agent from obeying commands hidden within the analyzed binaries or signal payloads.
- Capability inventory: The skill grants capabilities to disassemble code and reconstruct projects (Cargo.toml, CMakeLists.txt) based on interpreted binary content.
- Sanitization: There is no mention of sanitizing or filtering extracted strings or metadata from the processed binaries before they are processed by the LLM.
Audit Metadata