re-fw-rootfs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous shell commands to be executed in the agent's environment, including unpacking tools (unsquashfs, 7z, cpio), filesystem mounting, and analysis tools (grep, ripgrep, readelf, file).
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of firmware images and extracted filesystems.
- Ingestion points: The skill reads untrusted data from rootfs.img, rootfs.squashfs, and various configuration/script files within the extracted firmware directory (SKILL.md).
- Boundary markers: The instructions do not specify any boundary markers or delimiters when interpolating file contents into the agent's context.
- Capability inventory: The skill utilizes file system navigation (ls), file reading (cat), pattern searching (grep, rg), and binary inspection (file, readelf).
- Sanitization: No evidence of sanitization or escaping of external content is provided in the operational steps.
Audit Metadata