make-song

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it incorporates untrusted user data into a command-line execution without explicit boundary markers or sanitization.
  • Ingestion points: Untrusted data enters the agent context via the --prompt and --lyrics arguments in SKILL.md.
  • Boundary markers: No delimiters or instructions are provided to the agent to ignore instructions embedded within the user-provided lyrics or prompts.
  • Capability inventory: The skill executes a system command using pnpm neta, which represents a command execution capability.
  • Sanitization: There is no evidence of escaping, validation, or filtering of the external content before it is passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:48 AM