ruzzy
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download and install the 'ruzzy' and 'msgpack' gems from the public RubyGems registry.\n- [COMMAND_EXECUTION]: The skill involves executing shell commands to configure ASAN_OPTIONS and run ruby scripts with LD_PRELOAD. These are standard operations for coverage-guided fuzzing and memory safety analysis.\n- [PROMPT_INJECTION]: The skill defines an interface for processing untrusted data in fuzzing harnesses, creating a surface for indirect prompt injection.\n
- Ingestion points: The 'data' argument in the test_one_input lambda functions (SKILL.md).\n
- Boundary markers: None provided in the templates to differentiate between data and instructions.\n
- Capability inventory: The skill uses Ruzzy.fuzz and shell execution commands to facilitate testing (SKILL.md).\n
- Sanitization: No input sanitization is present, as the tool's purpose is to find vulnerabilities by processing malformed inputs.
Audit Metadata