skills/aeondave/malskill/c-bof/Gen Agent Trust Hub

c-bof

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The shell script scripts/build_bof.sh executes the x86_64-w64-mingw32-gcc compiler on C source files provided to the agent. This represents a functional capability for executing compilation tasks on the local system. \n- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface where the agent generates and compiles code based on potentially untrusted user input. \n
  • Ingestion points: User prompts requesting BOF creation or modification as described in SKILL.md. \n
  • Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the user-provided logic. \n
  • Capability inventory: The skill possesses the capability to write C files and execute a compiler via scripts/build_bof.sh. \n
  • Sanitization: Absent; the skill does not specify methods for validating or escaping generated C code before compilation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 08:19 PM
Security Audit — agent-trust-hub — c-bof