maestro-learn

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted user input from $ARGUMENTS to determine routing logic and command execution parameters. It lacks boundary markers or instructions to ignore instructions embedded within the intent text.\n
  • Ingestion points: SKILL.md (Context section) captures user intent in $ARGUMENTS.\n
  • Boundary markers: None identified in the provided instructions.\n
  • Capability inventory: The skill utilizes the Bash tool to execute secondary commands (learn-follow, learn-investigate, etc.).\n
  • Sanitization: No input validation or escaping mechanisms are described for the interpolated arguments.\n- [COMMAND_EXECUTION]: The execution logic involves mapping user keywords to shell invocations. This pattern of interpolating user-provided text directly into command lines is a surface for command injection if the agent does not apply strict escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 08:44 AM
Security Audit — agent-trust-hub — maestro-learn