cli-forge-extend

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard Rust verification commands (cargo build, cargo test, cargo clippy, cargo fmt) within the generated project. This is expected behavior for developer-focused automation.\n- [EXTERNAL_DOWNLOADS]: The skill adds well-known dependencies (uuid, libc, rustyline) to the project's Cargo.toml. These crates are standard in the Rust ecosystem.\n- [DATA_EXFILTRATION]: The daemon implementation uses Unix Domain Sockets for local IPC. In templates/daemon.rs.tpl, the socket directory is created with restricted (0700) permissions, effectively preventing access by other local users and ensuring secure inter-process communication.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection due to its core function of processing and executing commands against existing project files.\n
  • Ingestion points: Reads files from the user-provided project directory (e.g., Cargo.toml, SKILL.md, source files).\n
  • Boundary markers: No explicit delimiter or protection mechanisms are used during file ingestion.\n
  • Capability inventory: The skill has the ability to write to the local filesystem and execute arbitrary shell commands via the cargo toolset.\n
  • Sanitization: The skill relies on standard Rust compilation and linting to detect structural issues in the generated code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 08:47 AM
Security Audit — agent-trust-hub — cli-forge-extend