skills/huiali/rust-skills/rust-ebpf/Gen Agent Trust Hub

rust-ebpf

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data via network packets (XDP Context).
  • Ingestion points: SKILL.md and SKILL_ZH.md define an entry point xdp_packet_counter(ctx: XdpContext) which receives raw network data.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content within packet data are provided in the examples.
  • Capability inventory: The skill enables the agent to load eBPF programs into the kernel and attach them to network interfaces like eth0 using the aya library.
  • Sanitization: The provided examples demonstrate counting and IP blocking but do not include sanitization logic for packet payloads.
  • [COMMAND_EXECUTION]: The skill includes standard Rust development and verification commands.
  • Evidence: SKILL_EN.md lists cargo build --release, cargo test, and cargo clippy for project validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:35 AM