skills/malue-ai/dazee-small/sag/Gen Agent Trust Hub

sag

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata includes an installation command that fetches the 'sag' utility from a third-party Homebrew tap ('steipete/tap/sag').
  • [COMMAND_EXECUTION]: The skill uses shell commands to invoke the 'sag' binary, passing user-provided strings as arguments to generate speech audio.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to the direct interpolation of untrusted user input into shell commands.
  • Ingestion points: User-provided text content intended for conversion to speech in SKILL.md.
  • Boundary markers: The command template uses double quotes to wrap the input string.
  • Capability inventory: The skill has the ability to execute the 'sag' subprocess and write audio files to the system's temporary directory.
  • Sanitization: No explicit shell escaping or input validation is specified in the skill's instructions to prevent command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 04:20 PM